Model registrykdeps asset
kdeps-models-llamafile
v1.0.5kdeps model: llamafile
Install
A kdeps asset: kdeps installs it on first run and updates it without a new release.
kdeps update models/llamafile
Pin a version with kdeps update models/llamafile@<version>.
Contents
142 models
| Alias | Params | Quant | Size | Description |
|---|---|---|---|---|
| qwen2.5 | 0.5B | Q4_K_M | 706 MB | Qwen2.5-0.5B-Instruct-Q4_K_M [default] |
| granite34 | 34B | Q5_0 | 23.4 GB | granite-34b-code-instruct.Q5_0 [default] |
| olmo7 | 7B | Q4_K_M | 4.5 GB | OLMo-7B-0424.Q4_K_M [default] |
| mathstral7 | 7B | Q4_K_M | 4.4 GB | mathstral-7B-v0.1.Q4_K_M [default] |
| gemma2 | 2B | Q4_K_M | 2.0 GB | gemma-2-2b-it.Q4_K_M [default] |
| rocket3 | 3B | Q4_K_M | 1.7 GB | rocket-3b.Q4_K_M [default] |
| llama3.2 | 1B | Q4_K_M | 1.1 GB | Llama-3.2-1B-Instruct-Q4_K_M [default] |
| llama3.1 | 8B | Q4_K_M | 5.2 GB | Meta-Llama-3.1-8B-Instruct.Q4_K_M [default] |
| llava1.6 | 7B | Q4_K_M | 5.2 GB | llava-v1.6-mistral-7b-Q4_K_M [default] |
| gemma4 | 31B | Q5_K_M | 23.1 GB | gemma-4-31B-it-Q5_K_M [default] |
| qwen3.8 | 27B | Q4_K_XL | 19.1 GB | Qwen3.8-27B-UD-Q4_K_XL [default] |
| qwen3.6 | 27B | Q4_K_M | 18.0 GB | Qwen3.6-27B-Q4_K_M [default] |
| qwen3.5 | 0.8B | Q8_0 | 1.2 GB | Qwen3.5-0.8B-Q8_0 [default] |
| ministral3 | 3B | Q4_K_M | 3.2 GB | Ministral-3-3B-Instruct-2512-Q4_K_M [default] |
| lfm2 | 24B | Q5_K_M | 17.2 GB | LFM2-24B-A2B-Q5_K_M [default] |
| mistral7 | 7B | Q4_K_M | 4.4 GB | mistral-7b-instruct-v0.2.Q4_K_M [default] |
| llama3 | 8B | Q4_K_M | 5.0 GB | Meta-Llama-3-8B-Instruct.Q4_K_M [default] |
| tinyllama1.1 | 1.1B | Q4_K_M | 911 MB | TinyLlama-1.1B-Chat-v1.0.Q4_K_M [default] |
| tinyllama1.1:1.1b | 1.1B | Q4_K_M | 911 MB | TinyLlama-1.1B-Chat-v1.0.Q4_K_M |
| tinyllama1.1:1.1b-q4 | 1.1B | Q4_K_M | 911 MB | TinyLlama-1.1B-Chat-v1.0.Q4_K_M |
| tinyllama1.1:1.1b-q2 | 1.1B | Q2_K | 675 MB | TinyLlama-1.1B-Chat-v1.0.Q2_K |
| tinyllama1.1:1.1b-q3 | 1.1B | Q3_K_M | 791 MB | TinyLlama-1.1B-Chat-v1.0.Q3_K_M |
| tinyllama1.1:1.1b-q5 | 1.1B | Q5_K_M | 1.0 GB | TinyLlama-1.1B-Chat-v1.0.Q5_K_M |
| tinyllama1.1:1.1b-q6 | 1.1B | Q6_K | 1.1 GB | TinyLlama-1.1B-Chat-v1.0.Q6_K |
| tinyllama1.1:1.1b-q8 | 1.1B | Q8_0 | 1.4 GB | TinyLlama-1.1B-Chat-v1.0.Q8_0 |
| llama3:8b | 8B | Q4_K_M | 5.0 GB | Meta-Llama-3-8B-Instruct.Q4_K_M |
| llama3:8b-q4 | 8B | Q4_K_M | 5.0 GB | Meta-Llama-3-8B-Instruct.Q4_K_M |
| llama3:8b-q2 | 8B | Q2_K | 3.2 GB | Meta-Llama-3-8B-Instruct.Q2_K |
| llama3:8b-q3 | 8B | Q3_K_M | 4.0 GB | Meta-Llama-3-8B-Instruct.Q3_K_M |
| llama3:8b-q5 | 8B | Q5_K_M | 5.8 GB | Meta-Llama-3-8B-Instruct.Q5_K_M |
| llama3:8b-q6 | 8B | Q6_K | 6.6 GB | Meta-Llama-3-8B-Instruct.Q6_K |
| llama3:8b-q8 | 8B | Q8_0 | 8.6 GB | Meta-Llama-3-8B-Instruct.Q8_0 |
| mistral7:7b | 7B | Q4_K_M | 4.4 GB | mistral-7b-instruct-v0.2.Q4_K_M |
| mistral7:7b-q4 | 7B | Q4_K_M | 4.4 GB | mistral-7b-instruct-v0.2.Q4_K_M |
| mistral7:7b-q2 | 7B | Q2_K | 2.8 GB | mistral-7b-instruct-v0.2.Q2_K |
| mistral7:7b-q3 | 7B | Q3_K_M | 3.6 GB | mistral-7b-instruct-v0.2.Q3_K_M |
| mistral7:7b-q5 | 7B | Q5_K_M | 5.2 GB | mistral-7b-instruct-v0.2.Q5_K_M |
| mistral7:7b-q6 | 7B | Q6_K | 6.0 GB | mistral-7b-instruct-v0.2.Q6_K |
| mistral7:7b-q8 | 7B | Q8_0 | 7.7 GB | mistral-7b-instruct-v0.2.Q8_0 |
| lfm2:24b | 24B | Q5_K_M | 17.2 GB | LFM2-24B-A2B-Q5_K_M |
| lfm2:24b-q5 | 24B | Q5_K_M | 17.2 GB | LFM2-24B-A2B-Q5_K_M |
| ministral3:3b | 3B | Q4_K_M | 3.2 GB | Ministral-3-3B-Instruct-2512-Q4_K_M |
| ministral3:3b-q4 | 3B | Q4_K_M | 3.2 GB | Ministral-3-3B-Instruct-2512-Q4_K_M |
| qwen3.5:0.8b | 0.8B | Q8_0 | 1.2 GB | Qwen3.5-0.8B-Q8_0 |
| qwen3.5:0.8b-q8 | 0.8B | Q8_0 | 1.2 GB | Qwen3.5-0.8B-Q8_0 |
| qwen3.5:2b | 2B | Q8_0 | 2.9 GB | Qwen3.5-2B-Q8_0 |
| qwen3.5:2b-q8 | 2B | Q8_0 | 2.9 GB | Qwen3.5-2B-Q8_0 |
| qwen3.5:4b | 4B | Q5_K_S | 3.9 GB | Qwen3.5-4B-Q5_K_S |
| qwen3.5:4b-q5 | 4B | Q5_K_S | 3.9 GB | Qwen3.5-4B-Q5_K_S |
| qwen3.5:9b | 9B | Q5_K_S | 7.5 GB | Qwen3.5-9B-Q5_K_S |
| qwen3.5:9b-q5 | 9B | Q5_K_S | 7.5 GB | Qwen3.5-9B-Q5_K_S |
| qwen3.6:27b | 27B | Q4_K_M | 18.0 GB | Qwen3.6-27B-Q4_K_M |
| qwen3.6:27b-q4 | 27B | Q4_K_M | 18.0 GB | Qwen3.6-27B-Q4_K_M |
| qwen3.8:27b | 27B | Q4_K_XL | 19.1 GB | Qwen3.8-27B-UD-Q4_K_XL |
| qwen3.8:27b-q4 | 27B | Q4_K_XL | 19.1 GB | Qwen3.8-27B-UD-Q4_K_XL |
| gemma4:31b | 31B | Q5_K_M | 23.1 GB | gemma-4-31B-it-Q5_K_M |
| gemma4:31b-q5 | 31B | Q5_K_M | 23.1 GB | gemma-4-31B-it-Q5_K_M |
| llava1.6:7b | 7B | Q4_K_M | 5.2 GB | llava-v1.6-mistral-7b-Q4_K_M |
| llava1.6:7b-q4 | 7B | Q4_K_M | 5.2 GB | llava-v1.6-mistral-7b-Q4_K_M |
| llava1.6:7b-q8 | 7B | Q8_0 | 8.5 GB | llava-v1.6-mistral-7b-Q8_0 |
| llama3.1:8b | 8B | Q4_K_M | 5.2 GB | Meta-Llama-3.1-8B-Instruct.Q4_K_M |
| llama3.1:8b-q4 | 8B | Q4_K_M | 5.2 GB | Meta-Llama-3.1-8B-Instruct.Q4_K_M |
| llama3.1:8b-q2 | 8B | Q2_K | 3.5 GB | Meta-Llama-3.1-8B-Instruct.Q2_K |
| llama3.1:8b-q3 | 8B | Q3_K_M | 4.3 GB | Meta-Llama-3.1-8B-Instruct.Q3_K_M |
| llama3.1:8b-q5 | 8B | Q5_K_M | 6.0 GB | Meta-Llama-3.1-8B-Instruct.Q5_K_M |
| llama3.1:8b-q6 | 8B | Q6_K | 6.9 GB | Meta-Llama-3.1-8B-Instruct.Q6_K |
| llama3.1:8b-q8 | 8B | Q8_0 | 8.8 GB | Meta-Llama-3.1-8B-Instruct.Q8_0 |
| llama3.2:1b | 1B | Q4_K_M | 1.1 GB | Llama-3.2-1B-Instruct-Q4_K_M |
| llama3.2:1b-q4 | 1B | Q4_K_M | 1.1 GB | Llama-3.2-1B-Instruct-Q4_K_M |
| llama3.2:1b-q5 | 1B | Q5_K_M | 1.2 GB | Llama-3.2-1B-Instruct-Q5_K_M |
| llama3.2:1b-q6 | 1B | Q6_K | 1.3 GB | Llama-3.2-1B-Instruct-Q6_K |
| llama3.2:1b-q8 | 1B | Q8_0 | 1.6 GB | Llama-3.2-1B-Instruct-Q8_0 |
| rocket3:3b | 3B | Q4_K_M | 1.7 GB | rocket-3b.Q4_K_M |
| rocket3:3b-q4 | 3B | Q4_K_M | 1.7 GB | rocket-3b.Q4_K_M |
| rocket3:3b-q2 | 3B | Q2_K | 1.1 GB | rocket-3b.Q2_K |
| rocket3:3b-q3 | 3B | Q3_K_M | 1.4 GB | rocket-3b.Q3_K_M |
| rocket3:3b-q5 | 3B | Q5_K_M | 2.0 GB | rocket-3b.Q5_K_M |
| rocket3:3b-q6 | 3B | Q6_K | 2.3 GB | rocket-3b.Q6_K |
| rocket3:3b-q8 | 3B | Q8_0 | 3.0 GB | rocket-3b.Q8_0 |
| gemma2:9b | 9B | Q4_K_M | 5.9 GB | gemma-2-9b-it.Q4_K_M |
| gemma2:9b-q4 | 9B | Q4_K_M | 5.9 GB | gemma-2-9b-it.Q4_K_M |
| gemma2:9b-q2 | 9B | Q2_K | 4.0 GB | gemma-2-9b-it.Q2_K |
| gemma2:9b-q3 | 9B | Q3_K_M | 4.9 GB | gemma-2-9b-it.Q3_K_M |
| gemma2:9b-q5 | 9B | Q5_K_M | 6.8 GB | gemma-2-9b-it.Q5_K_M |
| gemma2:9b-q6 | 9B | Q6_K | 7.8 GB | gemma-2-9b-it.Q6_K |
| gemma2:9b-q8 | 9B | Q8_0 | 10.0 GB | gemma-2-9b-it.Q8_0 |
| mathstral7:7b | 7B | Q4_K_M | 4.4 GB | mathstral-7B-v0.1.Q4_K_M |
| mathstral7:7b-q4 | 7B | Q4_K_M | 4.4 GB | mathstral-7B-v0.1.Q4_K_M |
| mathstral7:7b-q2 | 7B | Q2_K | 2.8 GB | mathstral-7B-v0.1.Q2_K |
| mathstral7:7b-q3 | 7B | Q3_K_M | 3.6 GB | mathstral-7B-v0.1.Q3_K_M |
| mathstral7:7b-q5 | 7B | Q5_K_M | 5.2 GB | mathstral-7B-v0.1.Q5_K_M |
| mathstral7:7b-q6 | 7B | Q6_K | 6.0 GB | mathstral-7B-v0.1.Q6_K |
| mathstral7:7b-q8 | 7B | Q8_0 | 7.7 GB | mathstral-7B-v0.1.Q8_0 |
| gemma2:2b | 2B | Q4_K_M | 2.0 GB | gemma-2-2b-it.Q4_K_M |
| gemma2:2b-q4 | 2B | Q4_K_M | 2.0 GB | gemma-2-2b-it.Q4_K_M |
| gemma2:2b-q2 | 2B | Q2_K | 1.5 GB | gemma-2-2b-it.Q2_K |
| gemma2:2b-q3 | 2B | Q3_K_M | 1.7 GB | gemma-2-2b-it.Q3_K_M |
| gemma2:2b-q5 | 2B | Q5_K_M | 2.2 GB | gemma-2-2b-it.Q5_K_M |
| gemma2:2b-q6 | 2B | Q6_K | 2.4 GB | gemma-2-2b-it.Q6_K |
| gemma2:2b-q8 | 2B | Q8_0 | 3.0 GB | gemma-2-2b-it.Q8_0 |
| llama3.2:3b | 3B | Q4_K_M | 2.3 GB | Llama-3.2-3B-Instruct-Q4_K_M |
| llama3.2:3b-q4 | 3B | Q4_K_M | 2.3 GB | Llama-3.2-3B-Instruct-Q4_K_M |
| llama3.2:3b-q5 | 3B | Q5_K_M | 2.6 GB | Llama-3.2-3B-Instruct-Q5_K_M |
| llama3.2:3b-q6 | 3B | Q6_K | 3.0 GB | Llama-3.2-3B-Instruct-Q6_K |
| llama3.2:3b-q8 | 3B | Q8_0 | 3.7 GB | Llama-3.2-3B-Instruct-Q8_0 |
| olmo7:7b | 7B | Q4_K_M | 4.5 GB | OLMo-7B-0424.Q4_K_M |
| olmo7:7b-q4 | 7B | Q4_K_M | 4.5 GB | OLMo-7B-0424.Q4_K_M |
| olmo7:7b-q2 | 7B | Q2_K | 2.9 GB | OLMo-7B-0424.Q2_K |
| olmo7:7b-q3 | 7B | Q3_K_M | 3.7 GB | OLMo-7B-0424.Q3_K_M |
| olmo7:7b-q5 | 7B | Q5_K_M | 5.2 GB | OLMo-7B-0424.Q5_K_M |
| olmo7:7b-q6 | 7B | Q6_K | 6.0 GB | OLMo-7B-0424.Q6_K |
| olmo7:7b-q8 | 7B | Q8_0 | 7.6 GB | OLMo-7B-0424.Q8_0 |
| llama3.1:70b | 70B | Q4_K_M | 42.8 GB | Meta-Llama-3.1-70B-Instruct.Q4_K_M |
| llama3.1:70b-q4 | 70B | Q4_K_M | 42.8 GB | Meta-Llama-3.1-70B-Instruct.Q4_K_M |
| llama3.1:70b-q2 | 70B | Q2_K | 26.6 GB | Meta-Llama-3.1-70B-Instruct.Q2_K |
| llama3.1:70b-q3 | 70B | Q3_K_M | 34.5 GB | Meta-Llama-3.1-70B-Instruct.Q3_K_M |
| llama3.1:70b-q5 | 70B | Q5_0 | 48.9 GB | Meta-Llama-3.1-70B-Instruct.Q5_0 |
| llama3:70b | 70B | Q4_K_M | 42.5 GB | Meta-Llama-3-70B-Instruct.Q4_K_M |
| llama3:70b-q4 | 70B | Q4_K_M | 42.5 GB | Meta-Llama-3-70B-Instruct.Q4_K_M |
| llama3:70b-q2 | 70B | Q2_K | 26.4 GB | Meta-Llama-3-70B-Instruct.Q2_K |
| llama3:70b-q3 | 70B | Q3_K_M | 34.3 GB | Meta-Llama-3-70B-Instruct.Q3_K_M |
| llama3:70b-q5 | 70B | Q5_K_M | 50.0 GB | Meta-Llama-3-70B-Instruct.Q5_K_M |
| gemma2:27b | 27B | Q4_K_M | 16.8 GB | gemma-2-27b-it.Q4_K_M |
| gemma2:27b-q4 | 27B | Q4_K_M | 16.8 GB | gemma-2-27b-it.Q4_K_M |
| gemma2:27b-q2 | 27B | Q2_K | 10.6 GB | gemma-2-27b-it.Q2_K |
| gemma2:27b-q3 | 27B | Q3_K_M | 13.6 GB | gemma-2-27b-it.Q3_K_M |
| gemma2:27b-q5 | 27B | Q5_K_M | 19.6 GB | gemma-2-27b-it.Q5_K_M |
| gemma2:27b-q6 | 27B | Q6_K | 22.5 GB | gemma-2-27b-it.Q6_K |
| gemma2:27b-q8 | 27B | Q8_0 | 29.1 GB | gemma-2-27b-it.Q8_0 |
| granite34:34b | 34B | Q5_0 | 23.4 GB | granite-34b-code-instruct.Q5_0 |
| granite34:34b-q5 | 34B | Q5_0 | 23.4 GB | granite-34b-code-instruct.Q5_0 |
| granite34:34b-q8 | 34B | Q8_0 | 36.0 GB | granite-34b-code-instruct.Q8_0 |
| qwen2.5:7b | 7B | Q4_K_M | 5.0 GB | Qwen2.5.1-Coder-7B-Instruct-Q4_K_M |
| qwen2.5:7b-q4 | 7B | Q4_K_M | 5.0 GB | Qwen2.5.1-Coder-7B-Instruct-Q4_K_M |
| qwen2.5:7b-q5 | 7B | Q5_K_M | 5.8 GB | Qwen2.5.1-Coder-7B-Instruct-Q5_K_M |
| qwen2.5:7b-q6 | 7B | Q6_K | 6.6 GB | Qwen2.5.1-Coder-7B-Instruct-Q6_K |
| qwen2.5:7b-q8 | 7B | Q8_0 | 8.4 GB | Qwen2.5.1-Coder-7B-Instruct-Q8_0 |
| qwen2.5:0.5b | 0.5B | Q4_K_M | 706 MB | Qwen2.5-0.5B-Instruct-Q4_K_M |
| qwen2.5:0.5b-q4 | 0.5B | Q4_K_M | 706 MB | Qwen2.5-0.5B-Instruct-Q4_K_M |
| qwen2.5:0.5b-q5 | 0.5B | Q5_K_M | 728 MB | Qwen2.5-0.5B-Instruct-Q5_K_M |
| qwen2.5:0.5b-q6 | 0.5B | Q6_K | 813 MB | Qwen2.5-0.5B-Instruct-Q6_K |
| qwen2.5:0.5b-q8 | 0.5B | Q8_0 | 839 MB | Qwen2.5-0.5B-Instruct-Q8_0 |
# llamafile model registry: aliases usable in model: fields and /model.
# Generated by tools/llamafile-harvester/harvest.py from HuggingFace; do not edit by hand.
# Entries: 142
version: 1.0.5
llamafiles:
- alias: "qwen2.5"
description: "Qwen2.5-0.5B-Instruct-Q4_K_M [default]"
url: "https://huggingface.co/mozilla-ai/Qwen2.5-0.5B-Instruct-llamafile/resolve/main/Qwen2.5-0.5B-Instruct-Q4_K_M.llamafile"
quantization: "Q4_K_M"
size_bytes: 705583133
llama_version: "2.5"
params: "0.5B"
downloads: 140
pipeline_tag: "text-generation"
filename: "Qwen2.5-0.5B-Instruct-Q4_K_M.llamafile"
repo: "mozilla-ai/Qwen2.5-0.5B-Instruct-llamafile"
- alias: "granite34"
description: "granite-34b-code-instruct.Q5_0 [default]"
url: "https://huggingface.co/mozilla-ai/granite-34b-code-instruct-llamafile/resolve/main/granite-34b-code-instruct.Q5_0.llamafile"
quantization: "Q5_0"
size_bytes: 23433656503
llama_version: "34"
params: "34B"
downloads: 210
pipeline_tag: "text-generation"
filename: "granite-34b-code-instruct.Q5_0.llamafile"
repo: "mozilla-ai/granite-34b-code-instruct-llamafile"
- alias: "olmo7"
description: "OLMo-7B-0424.Q4_K_M [default]"
url: "https://huggingface.co/mozilla-ai/OLMo-7B-0424-llamafile/resolve/main/OLMo-7B-0424.Q4_K_M.llamafile"
quantization: "Q4_K_M"
size_bytes: 4492384268
llama_version: "7"
params: "7B"
downloads: 944
pipeline_tag: ""
filename: "OLMo-7B-0424.Q4_K_M.llamafile"
repo: "mozilla-ai/OLMo-7B-0424-llamafile"
- alias: "mathstral7"
description: "mathstral-7B-v0.1.Q4_K_M [default]"
url: "https://huggingface.co/mozilla-ai/mathstral-7B-v0.1-llamafile/resolve/main/mathstral-7B-v0.1.Q4_K_M.llamafile"
quantization: "Q4_K_M"
size_bytes: 4402788613
llama_version: "7"
params: "7B"
downloads: 1916
pipeline_tag: ""
filename: "mathstral-7B-v0.1.Q4_K_M.llamafile"
repo: "mozilla-ai/mathstral-7B-v0.1-llamafile"
- alias: "gemma2"
description: "gemma-2-2b-it.Q4_K_M [default]"
url: "https://huggingface.co/mozilla-ai/gemma-2-2b-it-llamafile/resolve/main/gemma-2-2b-it.Q4_K_M.llamafile"
quantization: "Q4_K_M"
size_bytes: 1951420702
llama_version: "2"
params: "2B"
downloads: 1708
pipeline_tag: ""
filename: "gemma-2-2b-it.Q4_K_M.llamafile"
repo: "mozilla-ai/gemma-2-2b-it-llamafile"
- alias: "rocket3"
description: "rocket-3b.Q4_K_M [default]"
url: "https://huggingface.co/mozilla-ai/rocket-3B-llamafile/resolve/main/rocket-3b.Q4_K_M.llamafile"
quantization: "Q4_K_M"
size_bytes: 1738553499
llama_version: "3"
params: "3B"
downloads: 2805
pipeline_tag: ""
filename: "rocket-3b.Q4_K_M.llamafile"
repo: "mozilla-ai/rocket-3B-llamafile"
- alias: "llama3.2"
description: "Llama-3.2-1B-Instruct-Q4_K_M [default]"
url: "https://huggingface.co/mozilla-ai/Llama-3.2-1B-Instruct-llamafile/resolve/main/Llama-3.2-1B-Instruct-Q4_K_M.llamafile"
quantization: "Q4_K_M"
size_bytes: 1115445277
llama_version: "3.2"
params: "1B"
downloads: 6203
pipeline_tag: ""
filename: "Llama-3.2-1B-Instruct-Q4_K_M.llamafile"
repo: "mozilla-ai/Llama-3.2-1B-Instruct-llamafile"
- alias: "llama3.1"
description: "Meta-Llama-3.1-8B-Instruct.Q4_K_M [default]"
url: "https://huggingface.co/mozilla-ai/Meta-Llama-3.1-8B-Instruct-llamafile/resolve/main/Meta-Llama-3.1-8B-Instruct.Q4_K_M.llamafile"
quantization: "Q4_K_M"
size_bytes: 5228484648
llama_version: "3.1"
params: "8B"
downloads: 7082
pipeline_tag: ""
filename: "Meta-Llama-3.1-8B-Instruct.Q4_K_M.llamafile"
repo: "mozilla-ai/Meta-Llama-3.1-8B-Instruct-llamafile"
- alias: "llava1.6"
description: "llava-v1.6-mistral-7b-Q4_K_M [default]"
url: "https://huggingface.co/mozilla-ai/llamafile_0.10/resolve/main/llava-v1.6-mistral-7b-Q4_K_M.llamafile"
quantization: "Q4_K_M"
size_bytes: 5203379210
llama_version: "1.6"
params: "7B"
downloads: 9212
pipeline_tag: ""
filename: "llava-v1.6-mistral-7b-Q4_K_M.llamafile"
repo: "mozilla-ai/llamafile_0.10"
- alias: "gemma4"
description: "gemma-4-31B-it-Q5_K_M [default]"
url: "https://huggingface.co/mozilla-ai/llamafile_0.10/resolve/main/gemma-4-31B-it-Q5_K_M.llamafile"
quantization: "Q5_K_M"
size_bytes: 23069541407
llama_version: "4"
params: "31B"
downloads: 9212
pipeline_tag: ""
filename: "gemma-4-31B-it-Q5_K_M.llamafile"
repo: "mozilla-ai/llamafile_0.10"
- alias: "qwen3.8"
description: "Qwen3.8-27B-UD-Q4_K_XL [default]"
url: "https://huggingface.co/mozilla-ai/llamafile_0.10/resolve/main/Qwen3.8-27B-UD-Q4_K_XL.llamafile"
quantization: "Q4_K_XL"
size_bytes: 19065029719
llama_version: "3.8"
params: "27B"
downloads: 9212
pipeline_tag: ""
filename: "Qwen3.8-27B-UD-Q4_K_XL.llamafile"
repo: "mozilla-ai/llamafile_0.10"
- alias: "qwen3.6"
description: "Qwen3.6-27B-Q4_K_M [default]"
url: "https://huggingface.co/mozilla-ai/llamafile_0.10/resolve/main/Qwen3.6-27B-Q4_K_M.llamafile"
quantization: "Q4_K_M"
size_bytes: 17958847569
llama_version: "3.6"
params: "27B"
downloads: 9212
pipeline_tag: ""
filename: "Qwen3.6-27B-Q4_K_M.llamafile"
repo: "mozilla-ai/llamafile_0.10"
- alias: "qwen3.5"
description: "Qwen3.5-0.8B-Q8_0 [default]"
url: "https://huggingface.co/mozilla-ai/llamafile_0.10/resolve/main/Qwen3.5-0.8B-Q8_0.llamafile"
quantization: "Q8_0"
size_bytes: 1229603934
llama_version: "3.5"
params: "0.8B"
downloads: 9212
pipeline_tag: ""
filename: "Qwen3.5-0.8B-Q8_0.llamafile"
repo: "mozilla-ai/llamafile_0.10"
- alias: "ministral3"
description: "Ministral-3-3B-Instruct-2512-Q4_K_M [default]"
url: "https://huggingface.co/mozilla-ai/llamafile_0.10/resolve/main/Ministral-3-3B-Instruct-2512-Q4_K_M.llamafile"
quantization: "Q4_K_M"
size_bytes: 3198960675
llama_version: "3"
params: "3B"
downloads: 9212
pipeline_tag: ""
filename: "Ministral-3-3B-Instruct-2512-Q4_K_M.llamafile"
repo: "mozilla-ai/llamafile_0.10"
- alias: "lfm2"
description: "LFM2-24B-A2B-Q5_K_M [default]"
url: "https://huggingface.co/mozilla-ai/llamafile_0.10/resolve/main/LFM2-24B-A2B-Q5_K_M.llamafile"
quantization: "Q5_K_M"
size_bytes: 17238932894
llama_version: "2"
params: "24B"
downloads: 9212
pipeline_tag: ""
filename: "LFM2-24B-A2B-Q5_K_M.llamafile"
repo: "mozilla-ai/llamafile_0.10"
- alias: "mistral7"
description: "mistral-7b-instruct-v0.2.Q4_K_M [default]"
url: "https://huggingface.co/mozilla-ai/Mistral-7B-Instruct-v0.2-llamafile/resolve/main/mistral-7b-instruct-v0.2.Q4_K_M.llamafile"
quantization: "Q4_K_M"
size_bytes: 4403968098
llama_version: "7"
params: "7B"
downloads: 11807
pipeline_tag: "text-generation"
filename: "mistral-7b-instruct-v0.2.Q4_K_M.llamafile"
repo: "mozilla-ai/Mistral-7B-Instruct-v0.2-llamafile"
- alias: "llama3"
description: "Meta-Llama-3-8B-Instruct.Q4_K_M [default]"
url: "https://huggingface.co/mozilla-ai/Meta-Llama-3-8B-Instruct-llamafile/resolve/main/Meta-Llama-3-8B-Instruct.Q4_K_M.llamafile"
quantization: "Q4_K_M"
size_bytes: 4950931850
llama_version: "3"
params: "8B"
downloads: 17134
pipeline_tag: "text-generation"
filename: "Meta-Llama-3-8B-Instruct.Q4_K_M.llamafile"
repo: "mozilla-ai/Meta-Llama-3-8B-Instruct-llamafile"
- alias: "tinyllama1.1"
description: "TinyLlama-1.1B-Chat-v1.0.Q4_K_M [default]"
url: "https://huggingface.co/mozilla-ai/TinyLlama-1.1B-Chat-v1.0-llamafile/resolve/main/TinyLlama-1.1B-Chat-v1.0.Q4_K_M.llamafile"
quantization: "Q4_K_M"
size_bytes: 910643427
llama_version: "1.1"
params: "1.1B"
downloads: 19605
pipeline_tag: ""
filename: "TinyLlama-1.1B-Chat-v1.0.Q4_K_M.llamafile"
repo: "mozilla-ai/TinyLlama-1.1B-Chat-v1.0-llamafile"
- alias: "tinyllama1.1:1.1b"
description: "TinyLlama-1.1B-Chat-v1.0.Q4_K_M"
url: "https://huggingface.co/mozilla-ai/TinyLlama-1.1B-Chat-v1.0-llamafile/resolve/main/TinyLlama-1.1B-Chat-v1.0.Q4_K_M.llamafile"
quantization: "Q4_K_M"
size_bytes: 910643427
llama_version: "1.1"
params: "1.1B"
downloads: 19605
pipeline_tag: ""
filename: "TinyLlama-1.1B-Chat-v1.0.Q4_K_M.llamafile"
repo: "mozilla-ai/TinyLlama-1.1B-Chat-v1.0-llamafile"
- alias: "tinyllama1.1:1.1b-q4"
description: "TinyLlama-1.1B-Chat-v1.0.Q4_K_M"
url: "https://huggingface.co/mozilla-ai/TinyLlama-1.1B-Chat-v1.0-llamafile/resolve/main/TinyLlama-1.1B-Chat-v1.0.Q4_K_M.llamafile"
quantization: "Q4_K_M"
size_bytes: 910643427
llama_version: "1.1"
params: "1.1B"
downloads: 19605
pipeline_tag: ""
filename: "TinyLlama-1.1B-Chat-v1.0.Q4_K_M.llamafile"
repo: "mozilla-ai/TinyLlama-1.1B-Chat-v1.0-llamafile"
- alias: "tinyllama1.1:1.1b-q2"
description: "TinyLlama-1.1B-Chat-v1.0.Q2_K"
url: "https://huggingface.co/mozilla-ai/TinyLlama-1.1B-Chat-v1.0-llamafile/resolve/main/TinyLlama-1.1B-Chat-v1.0.Q2_K.llamafile"
quantization: "Q2_K"
size_bytes: 674910431
llama_version: "1.1"
params: "1.1B"
downloads: 19605
pipeline_tag: ""
filename: "TinyLlama-1.1B-Chat-v1.0.Q2_K.llamafile"
repo: "mozilla-ai/TinyLlama-1.1B-Chat-v1.0-llamafile"
- alias: "tinyllama1.1:1.1b-q3"
description: "TinyLlama-1.1B-Chat-v1.0.Q3_K_M"
url: "https://huggingface.co/mozilla-ai/TinyLlama-1.1B-Chat-v1.0-llamafile/resolve/main/TinyLlama-1.1B-Chat-v1.0.Q3_K_M.llamafile"
quantization: "Q3_K_M"
size_bytes: 791236835
llama_version: "1.1"
params: "1.1B"
downloads: 19605
pipeline_tag: ""
filename: "TinyLlama-1.1B-Chat-v1.0.Q3_K_M.llamafile"
repo: "mozilla-ai/TinyLlama-1.1B-Chat-v1.0-llamafile"
- alias: "tinyllama1.1:1.1b-q5"
description: "TinyLlama-1.1B-Chat-v1.0.Q5_K_M"
url: "https://huggingface.co/mozilla-ai/TinyLlama-1.1B-Chat-v1.0-llamafile/resolve/main/TinyLlama-1.1B-Chat-v1.0.Q5_K_M.llamafile"
quantization: "Q5_K_M"
size_bytes: 1024872675
llama_version: "1.1"
params: "1.1B"
downloads: 19605
pipeline_tag: ""
filename: "TinyLlama-1.1B-Chat-v1.0.Q5_K_M.llamafile"
repo: "mozilla-ai/TinyLlama-1.1B-Chat-v1.0-llamafile"
- alias: "tinyllama1.1:1.1b-q6"
description: "TinyLlama-1.1B-Chat-v1.0.Q6_K"
url: "https://huggingface.co/mozilla-ai/TinyLlama-1.1B-Chat-v1.0-llamafile/resolve/main/TinyLlama-1.1B-Chat-v1.0.Q6_K.llamafile"
quantization: "Q6_K"
size_bytes: 1146245343
llama_version: "1.1"
params: "1.1B"
downloads: 19605
pipeline_tag: ""
filename: "TinyLlama-1.1B-Chat-v1.0.Q6_K.llamafile"
repo: "mozilla-ai/TinyLlama-1.1B-Chat-v1.0-llamafile"
- alias: "tinyllama1.1:1.1b-q8"
description: "TinyLlama-1.1B-Chat-v1.0.Q8_0"
url: "https://huggingface.co/mozilla-ai/TinyLlama-1.1B-Chat-v1.0-llamafile/resolve/main/TinyLlama-1.1B-Chat-v1.0.Q8_0.llamafile"
quantization: "Q8_0"
size_bytes: 1412583647
llama_version: "1.1"
params: "1.1B"
downloads: 19605
pipeline_tag: ""
filename: "TinyLlama-1.1B-Chat-v1.0.Q8_0.llamafile"
repo: "mozilla-ai/TinyLlama-1.1B-Chat-v1.0-llamafile"
- alias: "llama3:8b"
description: "Meta-Llama-3-8B-Instruct.Q4_K_M"
url: "https://huggingface.co/mozilla-ai/Meta-Llama-3-8B-Instruct-llamafile/resolve/main/Meta-Llama-3-8B-Instruct.Q4_K_M.llamafile"
quantization: "Q4_K_M"
size_bytes: 4950931850
llama_version: "3"
params: "8B"
downloads: 17134
pipeline_tag: "text-generation"
filename: "Meta-Llama-3-8B-Instruct.Q4_K_M.llamafile"
repo: "mozilla-ai/Meta-Llama-3-8B-Instruct-llamafile"
- alias: "llama3:8b-q4"
description: "Meta-Llama-3-8B-Instruct.Q4_K_M"
url: "https://huggingface.co/mozilla-ai/Meta-Llama-3-8B-Instruct-llamafile/resolve/main/Meta-Llama-3-8B-Instruct.Q4_K_M.llamafile"
quantization: "Q4_K_M"
size_bytes: 4950931850
llama_version: "3"
params: "8B"
downloads: 17134
pipeline_tag: "text-generation"
filename: "Meta-Llama-3-8B-Instruct.Q4_K_M.llamafile"
repo: "mozilla-ai/Meta-Llama-3-8B-Instruct-llamafile"
- alias: "llama3:8b-q2"
description: "Meta-Llama-3-8B-Instruct.Q2_K"
url: "https://huggingface.co/mozilla-ai/Meta-Llama-3-8B-Instruct-llamafile/resolve/main/Meta-Llama-3-8B-Instruct.Q2_K.llamafile"
quantization: "Q2_K"
size_bytes: 3209312646
llama_version: "3"
params: "8B"
downloads: 17134
pipeline_tag: "text-generation"
filename: "Meta-Llama-3-8B-Instruct.Q2_K.llamafile"
repo: "mozilla-ai/Meta-Llama-3-8B-Instruct-llamafile"
- alias: "llama3:8b-q3"
description: "Meta-Llama-3-8B-Instruct.Q3_K_M"
url: "https://huggingface.co/mozilla-ai/Meta-Llama-3-8B-Instruct-llamafile/resolve/main/Meta-Llama-3-8B-Instruct.Q3_K_M.llamafile"
quantization: "Q3_K_M"
size_bytes: 4049090954
llama_version: "3"
params: "8B"
downloads: 17134
pipeline_tag: "text-generation"
filename: "Meta-Llama-3-8B-Instruct.Q3_K_M.llamafile"
repo: "mozilla-ai/Meta-Llama-3-8B-Instruct-llamafile"
- alias: "llama3:8b-q5"
description: "Meta-Llama-3-8B-Instruct.Q5_K_M"
url: "https://huggingface.co/mozilla-ai/Meta-Llama-3-8B-Instruct-llamafile/resolve/main/Meta-Llama-3-8B-Instruct.Q5_K_M.llamafile"
quantization: "Q5_K_M"
size_bytes: 5763185034
llama_version: "3"
params: "8B"
downloads: 17134
pipeline_tag: "text-generation"
filename: "Meta-Llama-3-8B-Instruct.Q5_K_M.llamafile"
repo: "mozilla-ai/Meta-Llama-3-8B-Instruct-llamafile"
- alias: "llama3:8b-q6"
description: "Meta-Llama-3-8B-Instruct.Q6_K"
url: "https://huggingface.co/mozilla-ai/Meta-Llama-3-8B-Instruct-llamafile/resolve/main/Meta-Llama-3-8B-Instruct.Q6_K.llamafile"
quantization: "Q6_K"
size_bytes: 6626228614
llama_version: "3"
params: "8B"
downloads: 17134
pipeline_tag: "text-generation"
filename: "Meta-Llama-3-8B-Instruct.Q6_K.llamafile"
repo: "mozilla-ai/Meta-Llama-3-8B-Instruct-llamafile"
- alias: "llama3:8b-q8"
description: "Meta-Llama-3-8B-Instruct.Q8_0"
url: "https://huggingface.co/mozilla-ai/Meta-Llama-3-8B-Instruct-llamafile/resolve/main/Meta-Llama-3-8B-Instruct.Q8_0.llamafile"
quantization: "Q8_0"
size_bytes: 8570943878
llama_version: "3"
params: "8B"
downloads: 17134
pipeline_tag: "text-generation"
filename: "Meta-Llama-3-8B-Instruct.Q8_0.llamafile"
repo: "mozilla-ai/Meta-Llama-3-8B-Instruct-llamafile"
- alias: "mistral7:7b"
description: "mistral-7b-instruct-v0.2.Q4_K_M"
url: "https://huggingface.co/mozilla-ai/Mistral-7B-Instruct-v0.2-llamafile/resolve/main/mistral-7b-instruct-v0.2.Q4_K_M.llamafile"
quantization: "Q4_K_M"
size_bytes: 4403968098
llama_version: "7"
params: "7B"
downloads: 11807
pipeline_tag: "text-generation"
filename: "mistral-7b-instruct-v0.2.Q4_K_M.llamafile"
repo: "mozilla-ai/Mistral-7B-Instruct-v0.2-llamafile"
- alias: "mistral7:7b-q4"
description: "mistral-7b-instruct-v0.2.Q4_K_M"
url: "https://huggingface.co/mozilla-ai/Mistral-7B-Instruct-v0.2-llamafile/resolve/main/mistral-7b-instruct-v0.2.Q4_K_M.llamafile"
quantization: "Q4_K_M"
size_bytes: 4403968098
llama_version: "7"
params: "7B"
downloads: 11807
pipeline_tag: "text-generation"
filename: "mistral-7b-instruct-v0.2.Q4_K_M.llamafile"
repo: "mozilla-ai/Mistral-7B-Instruct-v0.2-llamafile"
- alias: "mistral7:7b-q2"
description: "mistral-7b-instruct-v0.2.Q2_K"
url: "https://huggingface.co/mozilla-ai/Mistral-7B-Instruct-v0.2-llamafile/resolve/main/mistral-7b-instruct-v0.2.Q2_K.llamafile"
quantization: "Q2_K"
size_bytes: 2754754654
llama_version: "7"
params: "7B"
downloads: 11807
pipeline_tag: "text-generation"
filename: "mistral-7b-instruct-v0.2.Q2_K.llamafile"
repo: "mozilla-ai/Mistral-7B-Instruct-v0.2-llamafile"
- alias: "mistral7:7b-q3"
description: "mistral-7b-instruct-v0.2.Q3_K_M"
url: "https://huggingface.co/mozilla-ai/Mistral-7B-Instruct-v0.2-llamafile/resolve/main/mistral-7b-instruct-v0.2.Q3_K_M.llamafile"
quantization: "Q3_K_M"
size_bytes: 3554490466
llama_version: "7"
params: "7B"
downloads: 11807
pipeline_tag: "text-generation"
filename: "mistral-7b-instruct-v0.2.Q3_K_M.llamafile"
repo: "mozilla-ai/Mistral-7B-Instruct-v0.2-llamafile"
- alias: "mistral7:7b-q5"
description: "mistral-7b-instruct-v0.2.Q5_K_M"
url: "https://huggingface.co/mozilla-ai/Mistral-7B-Instruct-v0.2-llamafile/resolve/main/mistral-7b-instruct-v0.2.Q5_K_M.llamafile"
quantization: "Q5_K_M"
size_bytes: 5166938210
llama_version: "7"
params: "7B"
downloads: 11807
pipeline_tag: "text-generation"
filename: "mistral-7b-instruct-v0.2.Q5_K_M.llamafile"
repo: "mozilla-ai/Mistral-7B-Instruct-v0.2-llamafile"
- alias: "mistral7:7b-q6"
description: "mistral-7b-instruct-v0.2.Q6_K"
url: "https://huggingface.co/mozilla-ai/Mistral-7B-Instruct-v0.2-llamafile/resolve/main/mistral-7b-instruct-v0.2.Q6_K.llamafile"
quantization: "Q6_K"
size_bytes: 5977552990
llama_version: "7"
params: "7B"
downloads: 11807
pipeline_tag: "text-generation"
filename: "mistral-7b-instruct-v0.2.Q6_K.llamafile"
repo: "mozilla-ai/Mistral-7B-Instruct-v0.2-llamafile"
- alias: "mistral7:7b-q8"
description: "mistral-7b-instruct-v0.2.Q8_0"
url: "https://huggingface.co/mozilla-ai/Mistral-7B-Instruct-v0.2-llamafile/resolve/main/mistral-7b-instruct-v0.2.Q8_0.llamafile"
quantization: "Q8_0"
size_bytes: 7731361886
llama_version: "7"
params: "7B"
downloads: 11807
pipeline_tag: "text-generation"
filename: "mistral-7b-instruct-v0.2.Q8_0.llamafile"
repo: "mozilla-ai/Mistral-7B-Instruct-v0.2-llamafile"
- alias: "lfm2:24b"
description: "LFM2-24B-A2B-Q5_K_M"
url: "https://huggingface.co/mozilla-ai/llamafile_0.10/resolve/main/LFM2-24B-A2B-Q5_K_M.llamafile"
quantization: "Q5_K_M"
size_bytes: 17238932894
llama_version: "2"
params: "24B"
downloads: 9212
pipeline_tag: ""
filename: "LFM2-24B-A2B-Q5_K_M.llamafile"
repo: "mozilla-ai/llamafile_0.10"
- alias: "lfm2:24b-q5"
description: "LFM2-24B-A2B-Q5_K_M"
url: "https://huggingface.co/mozilla-ai/llamafile_0.10/resolve/main/LFM2-24B-A2B-Q5_K_M.llamafile"
quantization: "Q5_K_M"
size_bytes: 17238932894
llama_version: "2"
params: "24B"
downloads: 9212
pipeline_tag: ""
filename: "LFM2-24B-A2B-Q5_K_M.llamafile"
repo: "mozilla-ai/llamafile_0.10"
- alias: "ministral3:3b"
description: "Ministral-3-3B-Instruct-2512-Q4_K_M"
url: "https://huggingface.co/mozilla-ai/llamafile_0.10/resolve/main/Ministral-3-3B-Instruct-2512-Q4_K_M.llamafile"
quantization: "Q4_K_M"
size_bytes: 3198960675
llama_version: "3"
params: "3B"
downloads: 9212
pipeline_tag: ""
filename: "Ministral-3-3B-Instruct-2512-Q4_K_M.llamafile"
repo: "mozilla-ai/llamafile_0.10"
- alias: "ministral3:3b-q4"
description: "Ministral-3-3B-Instruct-2512-Q4_K_M"
url: "https://huggingface.co/mozilla-ai/llamafile_0.10/resolve/main/Ministral-3-3B-Instruct-2512-Q4_K_M.llamafile"
quantization: "Q4_K_M"
size_bytes: 3198960675
llama_version: "3"
params: "3B"
downloads: 9212
pipeline_tag: ""
filename: "Ministral-3-3B-Instruct-2512-Q4_K_M.llamafile"
repo: "mozilla-ai/llamafile_0.10"
- alias: "qwen3.5:0.8b"
description: "Qwen3.5-0.8B-Q8_0"
url: "https://huggingface.co/mozilla-ai/llamafile_0.10/resolve/main/Qwen3.5-0.8B-Q8_0.llamafile"
quantization: "Q8_0"
size_bytes: 1229603934
llama_version: "3.5"
params: "0.8B"
downloads: 9212
pipeline_tag: ""
filename: "Qwen3.5-0.8B-Q8_0.llamafile"
repo: "mozilla-ai/llamafile_0.10"
- alias: "qwen3.5:0.8b-q8"
description: "Qwen3.5-0.8B-Q8_0"
url: "https://huggingface.co/mozilla-ai/llamafile_0.10/resolve/main/Qwen3.5-0.8B-Q8_0.llamafile"
quantization: "Q8_0"
size_bytes: 1229603934
llama_version: "3.5"
params: "0.8B"
downloads: 9212
pipeline_tag: ""
filename: "Qwen3.5-0.8B-Q8_0.llamafile"
repo: "mozilla-ai/llamafile_0.10"
- alias: "qwen3.5:2b"
description: "Qwen3.5-2B-Q8_0"
url: "https://huggingface.co/mozilla-ai/llamafile_0.10/resolve/main/Qwen3.5-2B-Q8_0.llamafile"
quantization: "Q8_0"
size_bytes: 2893825114
llama_version: "3.5"
params: "2B"
downloads: 9212
pipeline_tag: ""
filename: "Qwen3.5-2B-Q8_0.llamafile"
repo: "mozilla-ai/llamafile_0.10"
- alias: "qwen3.5:2b-q8"
description: "Qwen3.5-2B-Q8_0"
url: "https://huggingface.co/mozilla-ai/llamafile_0.10/resolve/main/Qwen3.5-2B-Q8_0.llamafile"
quantization: "Q8_0"
size_bytes: 2893825114
llama_version: "3.5"
params: "2B"
downloads: 9212
pipeline_tag: ""
filename: "Qwen3.5-2B-Q8_0.llamafile"
repo: "mozilla-ai/llamafile_0.10"
- alias: "qwen3.5:4b"
description: "Qwen3.5-4B-Q5_K_S"
url: "https://huggingface.co/mozilla-ai/llamafile_0.10/resolve/main/Qwen3.5-4B-Q5_K_S.llamafile"
quantization: "Q5_K_S"
size_bytes: 3910943838
llama_version: "3.5"
params: "4B"
downloads: 9212
pipeline_tag: ""
filename: "Qwen3.5-4B-Q5_K_S.llamafile"
repo: "mozilla-ai/llamafile_0.10"
- alias: "qwen3.5:4b-q5"
description: "Qwen3.5-4B-Q5_K_S"
url: "https://huggingface.co/mozilla-ai/llamafile_0.10/resolve/main/Qwen3.5-4B-Q5_K_S.llamafile"
quantization: "Q5_K_S"
size_bytes: 3910943838
llama_version: "3.5"
params: "4B"
downloads: 9212
pipeline_tag: ""
filename: "Qwen3.5-4B-Q5_K_S.llamafile"
repo: "mozilla-ai/llamafile_0.10"
- alias: "qwen3.5:9b"
description: "Qwen3.5-9B-Q5_K_S"
url: "https://huggingface.co/mozilla-ai/llamafile_0.10/resolve/main/Qwen3.5-9B-Q5_K_S.llamafile"
quantization: "Q5_K_S"
size_bytes: 7493338191
llama_version: "3.5"
params: "9B"
downloads: 9212
pipeline_tag: ""
filename: "Qwen3.5-9B-Q5_K_S.llamafile"
repo: "mozilla-ai/llamafile_0.10"
- alias: "qwen3.5:9b-q5"
description: "Qwen3.5-9B-Q5_K_S"
url: "https://huggingface.co/mozilla-ai/llamafile_0.10/resolve/main/Qwen3.5-9B-Q5_K_S.llamafile"
quantization: "Q5_K_S"
size_bytes: 7493338191
llama_version: "3.5"
params: "9B"
downloads: 9212
pipeline_tag: ""
filename: "Qwen3.5-9B-Q5_K_S.llamafile"
repo: "mozilla-ai/llamafile_0.10"
- alias: "qwen3.6:27b"
description: "Qwen3.6-27B-Q4_K_M"
url: "https://huggingface.co/mozilla-ai/llamafile_0.10/resolve/main/Qwen3.6-27B-Q4_K_M.llamafile"
quantization: "Q4_K_M"
size_bytes: 17958847569
llama_version: "3.6"
params: "27B"
downloads: 9212
pipeline_tag: ""
filename: "Qwen3.6-27B-Q4_K_M.llamafile"
repo: "mozilla-ai/llamafile_0.10"
- alias: "qwen3.6:27b-q4"
description: "Qwen3.6-27B-Q4_K_M"
url: "https://huggingface.co/mozilla-ai/llamafile_0.10/resolve/main/Qwen3.6-27B-Q4_K_M.llamafile"
quantization: "Q4_K_M"
size_bytes: 17958847569
llama_version: "3.6"
params: "27B"
downloads: 9212
pipeline_tag: ""
filename: "Qwen3.6-27B-Q4_K_M.llamafile"
repo: "mozilla-ai/llamafile_0.10"
- alias: "qwen3.8:27b"
description: "Qwen3.8-27B-UD-Q4_K_XL"
url: "https://huggingface.co/mozilla-ai/llamafile_0.10/resolve/main/Qwen3.8-27B-UD-Q4_K_XL.llamafile"
quantization: "Q4_K_XL"
size_bytes: 19065029719
llama_version: "3.8"
params: "27B"
downloads: 9212
pipeline_tag: ""
filename: "Qwen3.8-27B-UD-Q4_K_XL.llamafile"
repo: "mozilla-ai/llamafile_0.10"
- alias: "qwen3.8:27b-q4"
description: "Qwen3.8-27B-UD-Q4_K_XL"
url: "https://huggingface.co/mozilla-ai/llamafile_0.10/resolve/main/Qwen3.8-27B-UD-Q4_K_XL.llamafile"
quantization: "Q4_K_XL"
size_bytes: 19065029719
llama_version: "3.8"
params: "27B"
downloads: 9212
pipeline_tag: ""
filename: "Qwen3.8-27B-UD-Q4_K_XL.llamafile"
repo: "mozilla-ai/llamafile_0.10"
- alias: "gemma4:31b"
description: "gemma-4-31B-it-Q5_K_M"
url: "https://huggingface.co/mozilla-ai/llamafile_0.10/resolve/main/gemma-4-31B-it-Q5_K_M.llamafile"
quantization: "Q5_K_M"
size_bytes: 23069541407
llama_version: "4"
params: "31B"
downloads: 9212
pipeline_tag: ""
filename: "gemma-4-31B-it-Q5_K_M.llamafile"
repo: "mozilla-ai/llamafile_0.10"
- alias: "gemma4:31b-q5"
description: "gemma-4-31B-it-Q5_K_M"
url: "https://huggingface.co/mozilla-ai/llamafile_0.10/resolve/main/gemma-4-31B-it-Q5_K_M.llamafile"
quantization: "Q5_K_M"
size_bytes: 23069541407
llama_version: "4"
params: "31B"
downloads: 9212
pipeline_tag: ""
filename: "gemma-4-31B-it-Q5_K_M.llamafile"
repo: "mozilla-ai/llamafile_0.10"
- alias: "llava1.6:7b"
description: "llava-v1.6-mistral-7b-Q4_K_M"
url: "https://huggingface.co/mozilla-ai/llamafile_0.10/resolve/main/llava-v1.6-mistral-7b-Q4_K_M.llamafile"
quantization: "Q4_K_M"
size_bytes: 5203379210
llama_version: "1.6"
params: "7B"
downloads: 9212
pipeline_tag: ""
filename: "llava-v1.6-mistral-7b-Q4_K_M.llamafile"
repo: "mozilla-ai/llamafile_0.10"
- alias: "llava1.6:7b-q4"
description: "llava-v1.6-mistral-7b-Q4_K_M"
url: "https://huggingface.co/mozilla-ai/llamafile_0.10/resolve/main/llava-v1.6-mistral-7b-Q4_K_M.llamafile"
quantization: "Q4_K_M"
size_bytes: 5203379210
llama_version: "1.6"
params: "7B"
downloads: 9212
pipeline_tag: ""
filename: "llava-v1.6-mistral-7b-Q4_K_M.llamafile"
repo: "mozilla-ai/llamafile_0.10"
- alias: "llava1.6:7b-q8"
description: "llava-v1.6-mistral-7b-Q8_0"
url: "https://huggingface.co/mozilla-ai/llamafile_0.10/resolve/main/llava-v1.6-mistral-7b-Q8_0.llamafile"
quantization: "Q8_0"
size_bytes: 8530772998
llama_version: "1.6"
params: "7B"
downloads: 9212
pipeline_tag: ""
filename: "llava-v1.6-mistral-7b-Q8_0.llamafile"
repo: "mozilla-ai/llamafile_0.10"
- alias: "llama3.1:8b"
description: "Meta-Llama-3.1-8B-Instruct.Q4_K_M"
url: "https://huggingface.co/mozilla-ai/Meta-Llama-3.1-8B-Instruct-llamafile/resolve/main/Meta-Llama-3.1-8B-Instruct.Q4_K_M.llamafile"
quantization: "Q4_K_M"
size_bytes: 5228484648
llama_version: "3.1"
params: "8B"
downloads: 7082
pipeline_tag: ""
filename: "Meta-Llama-3.1-8B-Instruct.Q4_K_M.llamafile"
repo: "mozilla-ai/Meta-Llama-3.1-8B-Instruct-llamafile"
- alias: "llama3.1:8b-q4"
description: "Meta-Llama-3.1-8B-Instruct.Q4_K_M"
url: "https://huggingface.co/mozilla-ai/Meta-Llama-3.1-8B-Instruct-llamafile/resolve/main/Meta-Llama-3.1-8B-Instruct.Q4_K_M.llamafile"
quantization: "Q4_K_M"
size_bytes: 5228484648
llama_version: "3.1"
params: "8B"
downloads: 7082
pipeline_tag: ""
filename: "Meta-Llama-3.1-8B-Instruct.Q4_K_M.llamafile"
repo: "mozilla-ai/Meta-Llama-3.1-8B-Instruct-llamafile"
- alias: "llama3.1:8b-q2"
description: "Meta-Llama-3.1-8B-Instruct.Q2_K"
url: "https://huggingface.co/mozilla-ai/Meta-Llama-3.1-8B-Instruct-llamafile/resolve/main/Meta-Llama-3.1-8B-Instruct.Q2_K.llamafile"
quantization: "Q2_K"
size_bytes: 3486865444
llama_version: "3.1"
params: "8B"
downloads: 7082
pipeline_tag: ""
filename: "Meta-Llama-3.1-8B-Instruct.Q2_K.llamafile"
repo: "mozilla-ai/Meta-Llama-3.1-8B-Instruct-llamafile"
- alias: "llama3.1:8b-q3"
description: "Meta-Llama-3.1-8B-Instruct.Q3_K_M"
url: "https://huggingface.co/mozilla-ai/Meta-Llama-3.1-8B-Instruct-llamafile/resolve/main/Meta-Llama-3.1-8B-Instruct.Q3_K_M.llamafile"
quantization: "Q3_K_M"
size_bytes: 4326643752
llama_version: "3.1"
params: "8B"
downloads: 7082
pipeline_tag: ""
filename: "Meta-Llama-3.1-8B-Instruct.Q3_K_M.llamafile"
repo: "mozilla-ai/Meta-Llama-3.1-8B-Instruct-llamafile"
- alias: "llama3.1:8b-q5"
description: "Meta-Llama-3.1-8B-Instruct.Q5_K_M"
url: "https://huggingface.co/mozilla-ai/Meta-Llama-3.1-8B-Instruct-llamafile/resolve/main/Meta-Llama-3.1-8B-Instruct.Q5_K_M.llamafile"
quantization: "Q5_K_M"
size_bytes: 6040737832
llama_version: "3.1"
params: "8B"
downloads: 7082
pipeline_tag: ""
filename: "Meta-Llama-3.1-8B-Instruct.Q5_K_M.llamafile"
repo: "mozilla-ai/Meta-Llama-3.1-8B-Instruct-llamafile"
- alias: "llama3.1:8b-q6"
description: "Meta-Llama-3.1-8B-Instruct.Q6_K"
url: "https://huggingface.co/mozilla-ai/Meta-Llama-3.1-8B-Instruct-llamafile/resolve/main/Meta-Llama-3.1-8B-Instruct.Q6_K.llamafile"
quantization: "Q6_K"
size_bytes: 6903781412
llama_version: "3.1"
params: "8B"
downloads: 7082
pipeline_tag: ""
filename: "Meta-Llama-3.1-8B-Instruct.Q6_K.llamafile"
repo: "mozilla-ai/Meta-Llama-3.1-8B-Instruct-llamafile"
- alias: "llama3.1:8b-q8"
description: "Meta-Llama-3.1-8B-Instruct.Q8_0"
url: "https://huggingface.co/mozilla-ai/Meta-Llama-3.1-8B-Instruct-llamafile/resolve/main/Meta-Llama-3.1-8B-Instruct.Q8_0.llamafile"
quantization: "Q8_0"
size_bytes: 8848496676
llama_version: "3.1"
params: "8B"
downloads: 7082
pipeline_tag: ""
filename: "Meta-Llama-3.1-8B-Instruct.Q8_0.llamafile"
repo: "mozilla-ai/Meta-Llama-3.1-8B-Instruct-llamafile"
- alias: "llama3.2:1b"
description: "Llama-3.2-1B-Instruct-Q4_K_M"
url: "https://huggingface.co/mozilla-ai/Llama-3.2-1B-Instruct-llamafile/resolve/main/Llama-3.2-1B-Instruct-Q4_K_M.llamafile"
quantization: "Q4_K_M"
size_bytes: 1115445277
llama_version: "3.2"
params: "1B"
downloads: 6203
pipeline_tag: ""
filename: "Llama-3.2-1B-Instruct-Q4_K_M.llamafile"
repo: "mozilla-ai/Llama-3.2-1B-Instruct-llamafile"
- alias: "llama3.2:1b-q4"
description: "Llama-3.2-1B-Instruct-Q4_K_M"
url: "https://huggingface.co/mozilla-ai/Llama-3.2-1B-Instruct-llamafile/resolve/main/Llama-3.2-1B-Instruct-Q4_K_M.llamafile"
quantization: "Q4_K_M"
size_bytes: 1115445277
llama_version: "3.2"
params: "1B"
downloads: 6203
pipeline_tag: ""
filename: "Llama-3.2-1B-Instruct-Q4_K_M.llamafile"
repo: "mozilla-ai/Llama-3.2-1B-Instruct-llamafile"
- alias: "llama3.2:1b-q5"
description: "Llama-3.2-1B-Instruct-Q5_K_M"
url: "https://huggingface.co/mozilla-ai/Llama-3.2-1B-Instruct-llamafile/resolve/main/Llama-3.2-1B-Instruct-Q5_K_M.llamafile"
quantization: "Q5_K_M"
size_bytes: 1219254301
llama_version: "3.2"
params: "1B"
downloads: 6203
pipeline_tag: ""
filename: "Llama-3.2-1B-Instruct-Q5_K_M.llamafile"
repo: "mozilla-ai/Llama-3.2-1B-Instruct-llamafile"
- alias: "llama3.2:1b-q6"
description: "Llama-3.2-1B-Instruct-Q6_K"
url: "https://huggingface.co/mozilla-ai/Llama-3.2-1B-Instruct-llamafile/resolve/main/Llama-3.2-1B-Instruct-Q6_K.llamafile"
quantization: "Q6_K"
size_bytes: 1329551385
llama_version: "3.2"
params: "1B"
downloads: 6203
pipeline_tag: ""
filename: "Llama-3.2-1B-Instruct-Q6_K.llamafile"
repo: "mozilla-ai/Llama-3.2-1B-Instruct-llamafile"
- alias: "llama3.2:1b-q8"
description: "Llama-3.2-1B-Instruct-Q8_0"
url: "https://huggingface.co/mozilla-ai/Llama-3.2-1B-Instruct-llamafile/resolve/main/Llama-3.2-1B-Instruct-Q8_0.llamafile"
quantization: "Q8_0"
size_bytes: 1628854297
llama_version: "3.2"
params: "1B"
downloads: 6203
pipeline_tag: ""
filename: "Llama-3.2-1B-Instruct-Q8_0.llamafile"
repo: "mozilla-ai/Llama-3.2-1B-Instruct-llamafile"
- alias: "rocket3:3b"
description: "rocket-3b.Q4_K_M"
url: "https://huggingface.co/mozilla-ai/rocket-3B-llamafile/resolve/main/rocket-3b.Q4_K_M.llamafile"
quantization: "Q4_K_M"
size_bytes: 1738553499
llama_version: "3"
params: "3B"
downloads: 2805
pipeline_tag: ""
filename: "rocket-3b.Q4_K_M.llamafile"
repo: "mozilla-ai/rocket-3B-llamafile"
- alias: "rocket3:3b-q4"
description: "rocket-3b.Q4_K_M"
url: "https://huggingface.co/mozilla-ai/rocket-3B-llamafile/resolve/main/rocket-3b.Q4_K_M.llamafile"
quantization: "Q4_K_M"
size_bytes: 1738553499
llama_version: "3"
params: "3B"
downloads: 2805
pipeline_tag: ""
filename: "rocket-3b.Q4_K_M.llamafile"
repo: "mozilla-ai/rocket-3B-llamafile"
- alias: "rocket3:3b-q2"
description: "rocket-3b.Q2_K"
url: "https://huggingface.co/mozilla-ai/rocket-3B-llamafile/resolve/main/rocket-3b.Q2_K.llamafile"
quantization: "Q2_K"
size_bytes: 1113667735
llama_version: "3"
params: "3B"
downloads: 2805
pipeline_tag: ""
filename: "rocket-3b.Q2_K.llamafile"
repo: "mozilla-ai/rocket-3B-llamafile"
- alias: "rocket3:3b-q3"
description: "rocket-3b.Q3_K_M"
url: "https://huggingface.co/mozilla-ai/rocket-3B-llamafile/resolve/main/rocket-3b.Q3_K_M.llamafile"
quantization: "Q3_K_M"
size_bytes: 1421359259
llama_version: "3"
params: "3B"
downloads: 2805
pipeline_tag: ""
filename: "rocket-3b.Q3_K_M.llamafile"
repo: "mozilla-ai/rocket-3B-llamafile"
- alias: "rocket3:3b-q5"
description: "rocket-3b.Q5_K_M"
url: "https://huggingface.co/mozilla-ai/rocket-3B-llamafile/resolve/main/rocket-3b.Q5_K_M.llamafile"
quantization: "Q5_K_M"
size_bytes: 2023307419
llama_version: "3"
params: "3B"
downloads: 2805
pipeline_tag: ""
filename: "rocket-3b.Q5_K_M.llamafile"
repo: "mozilla-ai/rocket-3B-llamafile"
- alias: "rocket3:3b-q6"
description: "rocket-3b.Q6_K"
url: "https://huggingface.co/mozilla-ai/rocket-3B-llamafile/resolve/main/rocket-3b.Q6_K.llamafile"
quantization: "Q6_K"
size_bytes: 2325887127
llama_version: "3"
params: "3B"
downloads: 2805
pipeline_tag: ""
filename: "rocket-3b.Q6_K.llamafile"
repo: "mozilla-ai/rocket-3B-llamafile"
- alias: "rocket3:3b-q8"
description: "rocket-3b.Q8_0"
url: "https://huggingface.co/mozilla-ai/rocket-3B-llamafile/resolve/main/rocket-3b.Q8_0.llamafile"
quantization: "Q8_0"
size_bytes: 3002874007
llama_version: "3"
params: "3B"
downloads: 2805
pipeline_tag: ""
filename: "rocket-3b.Q8_0.llamafile"
repo: "mozilla-ai/rocket-3B-llamafile"
- alias: "gemma2:9b"
description: "gemma-2-9b-it.Q4_K_M"
url: "https://huggingface.co/mozilla-ai/gemma-2-9b-it-llamafile/resolve/main/gemma-2-9b-it.Q4_K_M.llamafile"
quantization: "Q4_K_M"
size_bytes: 5930891421
llama_version: "2"
params: "9B"
downloads: 1934
pipeline_tag: ""
filename: "gemma-2-9b-it.Q4_K_M.llamafile"
repo: "mozilla-ai/gemma-2-9b-it-llamafile"
- alias: "gemma2:9b-q4"
description: "gemma-2-9b-it.Q4_K_M"
url: "https://huggingface.co/mozilla-ai/gemma-2-9b-it-llamafile/resolve/main/gemma-2-9b-it.Q4_K_M.llamafile"
quantization: "Q4_K_M"
size_bytes: 5930891421
llama_version: "2"
params: "9B"
downloads: 1934
pipeline_tag: ""
filename: "gemma-2-9b-it.Q4_K_M.llamafile"
repo: "mozilla-ai/gemma-2-9b-it-llamafile"
- alias: "gemma2:9b-q2"
description: "gemma-2-9b-it.Q2_K"
url: "https://huggingface.co/mozilla-ai/gemma-2-9b-it-llamafile/resolve/main/gemma-2-9b-it.Q2_K.llamafile"
quantization: "Q2_K"
size_bytes: 3975231641
llama_version: "2"
params: "9B"
downloads: 1934
pipeline_tag: ""
filename: "gemma-2-9b-it.Q2_K.llamafile"
repo: "mozilla-ai/gemma-2-9b-it-llamafile"
- alias: "gemma2:9b-q3"
description: "gemma-2-9b-it.Q3_K_M"
url: "https://huggingface.co/mozilla-ai/gemma-2-9b-it-llamafile/resolve/main/gemma-2-9b-it.Q3_K_M.llamafile"
quantization: "Q3_K_M"
size_bytes: 4931664029
llama_version: "2"
params: "9B"
downloads: 1934
pipeline_tag: ""
filename: "gemma-2-9b-it.Q3_K_M.llamafile"
repo: "mozilla-ai/gemma-2-9b-it-llamafile"
- alias: "gemma2:9b-q5"
description: "gemma-2-9b-it.Q5_K_M"
url: "https://huggingface.co/mozilla-ai/gemma-2-9b-it-llamafile/resolve/main/gemma-2-9b-it.Q5_K_M.llamafile"
quantization: "Q5_K_M"
size_bytes: 6817200285
llama_version: "2"
params: "9B"
downloads: 1934
pipeline_tag: ""
filename: "gemma-2-9b-it.Q5_K_M.llamafile"
repo: "mozilla-ai/gemma-2-9b-it-llamafile"
- alias: "gemma2:9b-q6"
description: "gemma-2-9b-it.Q6_K"
url: "https://huggingface.co/mozilla-ai/gemma-2-9b-it-llamafile/resolve/main/gemma-2-9b-it.Q6_K.llamafile"
quantization: "Q6_K"
size_bytes: 7758952601
llama_version: "2"
params: "9B"
downloads: 1934
pipeline_tag: ""
filename: "gemma-2-9b-it.Q6_K.llamafile"
repo: "mozilla-ai/gemma-2-9b-it-llamafile"
- alias: "gemma2:9b-q8"
description: "gemma-2-9b-it.Q8_0"
url: "https://huggingface.co/mozilla-ai/gemma-2-9b-it-llamafile/resolve/main/gemma-2-9b-it.Q8_0.llamafile"
quantization: "Q8_0"
size_bytes: 9997007001
llama_version: "2"
params: "9B"
downloads: 1934
pipeline_tag: ""
filename: "gemma-2-9b-it.Q8_0.llamafile"
repo: "mozilla-ai/gemma-2-9b-it-llamafile"
- alias: "mathstral7:7b"
description: "mathstral-7B-v0.1.Q4_K_M"
url: "https://huggingface.co/mozilla-ai/mathstral-7B-v0.1-llamafile/resolve/main/mathstral-7B-v0.1.Q4_K_M.llamafile"
quantization: "Q4_K_M"
size_bytes: 4402788613
llama_version: "7"
params: "7B"
downloads: 1916
pipeline_tag: ""
filename: "mathstral-7B-v0.1.Q4_K_M.llamafile"
repo: "mozilla-ai/mathstral-7B-v0.1-llamafile"
- alias: "mathstral7:7b-q4"
description: "mathstral-7B-v0.1.Q4_K_M"
url: "https://huggingface.co/mozilla-ai/mathstral-7B-v0.1-llamafile/resolve/main/mathstral-7B-v0.1.Q4_K_M.llamafile"
quantization: "Q4_K_M"
size_bytes: 4402788613
llama_version: "7"
params: "7B"
downloads: 1916
pipeline_tag: ""
filename: "mathstral-7B-v0.1.Q4_K_M.llamafile"
repo: "mozilla-ai/mathstral-7B-v0.1-llamafile"
- alias: "mathstral7:7b-q2"
description: "mathstral-7B-v0.1.Q2_K"
url: "https://huggingface.co/mozilla-ai/mathstral-7B-v0.1-llamafile/resolve/main/mathstral-7B-v0.1.Q2_K.llamafile"
quantization: "Q2_K"
size_bytes: 2752854273
llama_version: "7"
params: "7B"
downloads: 1916
pipeline_tag: ""
filename: "mathstral-7B-v0.1.Q2_K.llamafile"
repo: "mozilla-ai/mathstral-7B-v0.1-llamafile"
- alias: "mathstral7:7b-q3"
description: "mathstral-7B-v0.1.Q3_K_M"
url: "https://huggingface.co/mozilla-ai/mathstral-7B-v0.1-llamafile/resolve/main/mathstral-7B-v0.1.Q3_K_M.llamafile"
quantization: "Q3_K_M"
size_bytes: 3552917765
llama_version: "7"
params: "7B"
downloads: 1916
pipeline_tag: ""
filename: "mathstral-7B-v0.1.Q3_K_M.llamafile"
repo: "mozilla-ai/mathstral-7B-v0.1-llamafile"
- alias: "mathstral7:7b-q5"
description: "mathstral-7B-v0.1.Q5_K_M"
url: "https://huggingface.co/mozilla-ai/mathstral-7B-v0.1-llamafile/resolve/main/mathstral-7B-v0.1.Q5_K_M.llamafile"
quantization: "Q5_K_M"
size_bytes: 5166151941
llama_version: "7"
params: "7B"
downloads: 1916
pipeline_tag: ""
filename: "mathstral-7B-v0.1.Q5_K_M.llamafile"
repo: "mozilla-ai/mathstral-7B-v0.1-llamafile"
- alias: "mathstral7:7b-q6"
description: "mathstral-7B-v0.1.Q6_K"
url: "https://huggingface.co/mozilla-ai/mathstral-7B-v0.1-llamafile/resolve/main/mathstral-7B-v0.1.Q6_K.llamafile"
quantization: "Q6_K"
size_bytes: 5977225473
llama_version: "7"
params: "7B"
downloads: 1916
pipeline_tag: ""
filename: "mathstral-7B-v0.1.Q6_K.llamafile"
repo: "mozilla-ai/mathstral-7B-v0.1-llamafile"
- alias: "mathstral7:7b-q8"
description: "mathstral-7B-v0.1.Q8_0"
url: "https://huggingface.co/mozilla-ai/mathstral-7B-v0.1-llamafile/resolve/main/mathstral-7B-v0.1.Q8_0.llamafile"
quantization: "Q8_0"
size_bytes: 7732541697
llama_version: "7"
params: "7B"
downloads: 1916
pipeline_tag: ""
filename: "mathstral-7B-v0.1.Q8_0.llamafile"
repo: "mozilla-ai/mathstral-7B-v0.1-llamafile"
- alias: "gemma2:2b"
description: "gemma-2-2b-it.Q4_K_M"
url: "https://huggingface.co/mozilla-ai/gemma-2-2b-it-llamafile/resolve/main/gemma-2-2b-it.Q4_K_M.llamafile"
quantization: "Q4_K_M"
size_bytes: 1951420702
llama_version: "2"
params: "2B"
downloads: 1708
pipeline_tag: ""
filename: "gemma-2-2b-it.Q4_K_M.llamafile"
repo: "mozilla-ai/gemma-2-2b-it-llamafile"
- alias: "gemma2:2b-q4"
description: "gemma-2-2b-it.Q4_K_M"
url: "https://huggingface.co/mozilla-ai/gemma-2-2b-it-llamafile/resolve/main/gemma-2-2b-it.Q4_K_M.llamafile"
quantization: "Q4_K_M"
size_bytes: 1951420702
llama_version: "2"
params: "2B"
downloads: 1708
pipeline_tag: ""
filename: "gemma-2-2b-it.Q4_K_M.llamafile"
repo: "mozilla-ai/gemma-2-2b-it-llamafile"
- alias: "gemma2:2b-q2"
description: "gemma-2-2b-it.Q2_K"
url: "https://huggingface.co/mozilla-ai/gemma-2-2b-it-llamafile/resolve/main/gemma-2-2b-it.Q2_K.llamafile"
quantization: "Q2_K"
size_bytes: 1472680218
llama_version: "2"
params: "2B"
downloads: 1708
pipeline_tag: ""
filename: "gemma-2-2b-it.Q2_K.llamafile"
repo: "mozilla-ai/gemma-2-2b-it-llamafile"
- alias: "gemma2:2b-q3"
description: "gemma-2-2b-it.Q3_K_M"
url: "https://huggingface.co/mozilla-ai/gemma-2-2b-it-llamafile/resolve/main/gemma-2-2b-it.Q3_K_M.llamafile"
quantization: "Q3_K_M"
size_bytes: 1704546590
llama_version: "2"
params: "2B"
downloads: 1708
pipeline_tag: ""
filename: "gemma-2-2b-it.Q3_K_M.llamafile"
repo: "mozilla-ai/gemma-2-2b-it-llamafile"
- alias: "gemma2:2b-q5"
description: "gemma-2-2b-it.Q5_K_M"
url: "https://huggingface.co/mozilla-ai/gemma-2-2b-it-llamafile/resolve/main/gemma-2-2b-it.Q5_K_M.llamafile"
quantization: "Q5_K_M"
size_bytes: 2166116638
llama_version: "2"
params: "2B"
downloads: 1708
pipeline_tag: ""
filename: "gemma-2-2b-it.Q5_K_M.llamafile"
repo: "mozilla-ai/gemma-2-2b-it-llamafile"
- alias: "gemma2:2b-q6"
description: "gemma-2-2b-it.Q6_K"
url: "https://huggingface.co/mozilla-ai/gemma-2-2b-it-llamafile/resolve/main/gemma-2-2b-it.Q6_K.llamafile"
quantization: "Q6_K"
size_bytes: 2394247450
llama_version: "2"
params: "2B"
downloads: 1708
pipeline_tag: ""
filename: "gemma-2-2b-it.Q6_K.llamafile"
repo: "mozilla-ai/gemma-2-2b-it-llamafile"
- alias: "gemma2:2b-q8"
description: "gemma-2-2b-it.Q8_0"
url: "https://huggingface.co/mozilla-ai/gemma-2-2b-it-llamafile/resolve/main/gemma-2-2b-it.Q8_0.llamafile"
quantization: "Q8_0"
size_bytes: 3027390746
llama_version: "2"
params: "2B"
downloads: 1708
pipeline_tag: ""
filename: "gemma-2-2b-it.Q8_0.llamafile"
repo: "mozilla-ai/gemma-2-2b-it-llamafile"
- alias: "llama3.2:3b"
description: "Llama-3.2-3B-Instruct-Q4_K_M"
url: "https://huggingface.co/mozilla-ai/Llama-3.2-3B-Instruct-llamafile/resolve/main/Llama-3.2-3B-Instruct-Q4_K_M.llamafile"
quantization: "Q4_K_M"
size_bytes: 2327140381
llama_version: "3.2"
params: "3B"
downloads: 1289
pipeline_tag: ""
filename: "Llama-3.2-3B-Instruct-Q4_K_M.llamafile"
repo: "mozilla-ai/Llama-3.2-3B-Instruct-llamafile"
- alias: "llama3.2:3b-q4"
description: "Llama-3.2-3B-Instruct-Q4_K_M"
url: "https://huggingface.co/mozilla-ai/Llama-3.2-3B-Instruct-llamafile/resolve/main/Llama-3.2-3B-Instruct-Q4_K_M.llamafile"
quantization: "Q4_K_M"
size_bytes: 2327140381
llama_version: "3.2"
params: "3B"
downloads: 1289
pipeline_tag: ""
filename: "Llama-3.2-3B-Instruct-Q4_K_M.llamafile"
repo: "mozilla-ai/Llama-3.2-3B-Instruct-llamafile"
- alias: "llama3.2:3b-q5"
description: "Llama-3.2-3B-Instruct-Q5_K_M"
url: "https://huggingface.co/mozilla-ai/Llama-3.2-3B-Instruct-llamafile/resolve/main/Llama-3.2-3B-Instruct-Q5_K_M.llamafile"
quantization: "Q5_K_M"
size_bytes: 2629916701
llama_version: "3.2"
params: "3B"
downloads: 1289
pipeline_tag: ""
filename: "Llama-3.2-3B-Instruct-Q5_K_M.llamafile"
repo: "mozilla-ai/Llama-3.2-3B-Instruct-llamafile"
- alias: "llama3.2:3b-q6"
description: "Llama-3.2-3B-Instruct-Q6_K"
url: "https://huggingface.co/mozilla-ai/Llama-3.2-3B-Instruct-llamafile/resolve/main/Llama-3.2-3B-Instruct-Q6_K.llamafile"
quantization: "Q6_K"
size_bytes: 2951632921
llama_version: "3.2"
params: "3B"
downloads: 1289
pipeline_tag: ""
filename: "Llama-3.2-3B-Instruct-Q6_K.llamafile"
repo: "mozilla-ai/Llama-3.2-3B-Instruct-llamafile"
- alias: "llama3.2:3b-q8"
description: "Llama-3.2-3B-Instruct-Q8_0"
url: "https://huggingface.co/mozilla-ai/Llama-3.2-3B-Instruct-llamafile/resolve/main/Llama-3.2-3B-Instruct-Q8_0.llamafile"
quantization: "Q8_0"
size_bytes: 3729676313
llama_version: "3.2"
params: "3B"
downloads: 1289
pipeline_tag: ""
filename: "Llama-3.2-3B-Instruct-Q8_0.llamafile"
repo: "mozilla-ai/Llama-3.2-3B-Instruct-llamafile"
- alias: "olmo7:7b"
description: "OLMo-7B-0424.Q4_K_M"
url: "https://huggingface.co/mozilla-ai/OLMo-7B-0424-llamafile/resolve/main/OLMo-7B-0424.Q4_K_M.llamafile"
quantization: "Q4_K_M"
size_bytes: 4492384268
llama_version: "7"
params: "7B"
downloads: 944
pipeline_tag: ""
filename: "OLMo-7B-0424.Q4_K_M.llamafile"
repo: "mozilla-ai/OLMo-7B-0424-llamafile"
- alias: "olmo7:7b-q4"
description: "OLMo-7B-0424.Q4_K_M"
url: "https://huggingface.co/mozilla-ai/OLMo-7B-0424-llamafile/resolve/main/OLMo-7B-0424.Q4_K_M.llamafile"
quantization: "Q4_K_M"
size_bytes: 4492384268
llama_version: "7"
params: "7B"
downloads: 944
pipeline_tag: ""
filename: "OLMo-7B-0424.Q4_K_M.llamafile"
repo: "mozilla-ai/OLMo-7B-0424-llamafile"
- alias: "olmo7:7b-q2"
description: "OLMo-7B-0424.Q2_K"
url: "https://huggingface.co/mozilla-ai/OLMo-7B-0424-llamafile/resolve/main/OLMo-7B-0424.Q2_K.llamafile"
quantization: "Q2_K"
size_bytes: 2926663688
llama_version: "7"
params: "7B"
downloads: 944
pipeline_tag: ""
filename: "OLMo-7B-0424.Q2_K.llamafile"
repo: "mozilla-ai/OLMo-7B-0424-llamafile"
- alias: "olmo7:7b-q3"
description: "OLMo-7B-0424.Q3_K_M"
url: "https://huggingface.co/mozilla-ai/OLMo-7B-0424-llamafile/resolve/main/OLMo-7B-0424.Q3_K_M.llamafile"
quantization: "Q3_K_M"
size_bytes: 3699464204
llama_version: "7"
params: "7B"
downloads: 944
pipeline_tag: ""
filename: "OLMo-7B-0424.Q3_K_M.llamafile"
repo: "mozilla-ai/OLMo-7B-0424-llamafile"
- alias: "olmo7:7b-q5"
description: "OLMo-7B-0424.Q5_K_M"
url: "https://huggingface.co/mozilla-ai/OLMo-7B-0424-llamafile/resolve/main/OLMo-7B-0424.Q5_K_M.llamafile"
quantization: "Q5_K_M"
size_bytes: 5203908620
llama_version: "7"
params: "7B"
downloads: 944
pipeline_tag: ""
filename: "OLMo-7B-0424.Q5_K_M.llamafile"
repo: "mozilla-ai/OLMo-7B-0424-llamafile"
- alias: "olmo7:7b-q6"
description: "OLMo-7B-0424.Q6_K"
url: "https://huggingface.co/mozilla-ai/OLMo-7B-0424-llamafile/resolve/main/OLMo-7B-0424.Q6_K.llamafile"
quantization: "Q6_K"
size_bytes: 5959931912
llama_version: "7"
params: "7B"
downloads: 944
pipeline_tag: ""
filename: "OLMo-7B-0424.Q6_K.llamafile"
repo: "mozilla-ai/OLMo-7B-0424-llamafile"
- alias: "olmo7:7b-q8"
description: "OLMo-7B-0424.Q8_0"
url: "https://huggingface.co/mozilla-ai/OLMo-7B-0424-llamafile/resolve/main/OLMo-7B-0424.Q8_0.llamafile"
quantization: "Q8_0"
size_bytes: 7628150792
llama_version: "7"
params: "7B"
downloads: 944
pipeline_tag: ""
filename: "OLMo-7B-0424.Q8_0.llamafile"
repo: "mozilla-ai/OLMo-7B-0424-llamafile"
- alias: "llama3.1:70b"
description: "Meta-Llama-3.1-70B-Instruct.Q4_K_M"
url: "https://huggingface.co/mozilla-ai/Meta-Llama-3.1-70B-Instruct-llamafile/resolve/main/Meta-Llama-3.1-70B-Instruct.Q4_K_M.llamafile"
quantization: "Q4_K_M"
size_bytes: 42763243834
llama_version: "3.1"
params: "70B"
downloads: 732
pipeline_tag: ""
filename: "Meta-Llama-3.1-70B-Instruct.Q4_K_M.llamafile"
repo: "mozilla-ai/Meta-Llama-3.1-70B-Instruct-llamafile"
- alias: "llama3.1:70b-q4"
description: "Meta-Llama-3.1-70B-Instruct.Q4_K_M"
url: "https://huggingface.co/mozilla-ai/Meta-Llama-3.1-70B-Instruct-llamafile/resolve/main/Meta-Llama-3.1-70B-Instruct.Q4_K_M.llamafile"
quantization: "Q4_K_M"
size_bytes: 42763243834
llama_version: "3.1"
params: "70B"
downloads: 732
pipeline_tag: ""
filename: "Meta-Llama-3.1-70B-Instruct.Q4_K_M.llamafile"
repo: "mozilla-ai/Meta-Llama-3.1-70B-Instruct-llamafile"
- alias: "llama3.1:70b-q2"
description: "Meta-Llama-3.1-70B-Instruct.Q2_K"
url: "https://huggingface.co/mozilla-ai/Meta-Llama-3.1-70B-Instruct-llamafile/resolve/main/Meta-Llama-3.1-70B-Instruct.Q2_K.llamafile"
quantization: "Q2_K"
size_bytes: 26617991478
llama_version: "3.1"
params: "70B"
downloads: 732
pipeline_tag: ""
filename: "Meta-Llama-3.1-70B-Instruct.Q2_K.llamafile"
repo: "mozilla-ai/Meta-Llama-3.1-70B-Instruct-llamafile"
- alias: "llama3.1:70b-q3"
description: "Meta-Llama-3.1-70B-Instruct.Q3_K_M"
url: "https://huggingface.co/mozilla-ai/Meta-Llama-3.1-70B-Instruct-llamafile/resolve/main/Meta-Llama-3.1-70B-Instruct.Q3_K_M.llamafile"
quantization: "Q3_K_M"
size_bytes: 34510360890
llama_version: "3.1"
params: "70B"
downloads: 732
pipeline_tag: ""
filename: "Meta-Llama-3.1-70B-Instruct.Q3_K_M.llamafile"
repo: "mozilla-ai/Meta-Llama-3.1-70B-Instruct-llamafile"
- alias: "llama3.1:70b-q5"
description: "Meta-Llama-3.1-70B-Instruct.Q5_0"
url: "https://huggingface.co/mozilla-ai/Meta-Llama-3.1-70B-Instruct-llamafile/resolve/main/Meta-Llama-3.1-70B-Instruct.Q5_0.llamafile"
quantization: "Q5_0"
size_bytes: 48900297014
llama_version: "3.1"
params: "70B"
downloads: 732
pipeline_tag: ""
filename: "Meta-Llama-3.1-70B-Instruct.Q5_0.llamafile"
repo: "mozilla-ai/Meta-Llama-3.1-70B-Instruct-llamafile"
- alias: "llama3:70b"
description: "Meta-Llama-3-70B-Instruct.Q4_K_M"
url: "https://huggingface.co/mozilla-ai/Meta-Llama-3-70B-Instruct-llamafile/resolve/main/Meta-Llama-3-70B-Instruct.Q4_K_M.llamafile"
quantization: "Q4_K_M"
size_bytes: 42549786921
llama_version: "3"
params: "70B"
downloads: 232
pipeline_tag: "text-generation"
filename: "Meta-Llama-3-70B-Instruct.Q4_K_M.llamafile"
repo: "mozilla-ai/Meta-Llama-3-70B-Instruct-llamafile"
- alias: "llama3:70b-q4"
description: "Meta-Llama-3-70B-Instruct.Q4_K_M"
url: "https://huggingface.co/mozilla-ai/Meta-Llama-3-70B-Instruct-llamafile/resolve/main/Meta-Llama-3-70B-Instruct.Q4_K_M.llamafile"
quantization: "Q4_K_M"
size_bytes: 42549786921
llama_version: "3"
params: "70B"
downloads: 232
pipeline_tag: "text-generation"
filename: "Meta-Llama-3-70B-Instruct.Q4_K_M.llamafile"
repo: "mozilla-ai/Meta-Llama-3-70B-Instruct-llamafile"
- alias: "llama3:70b-q2"
description: "Meta-Llama-3-70B-Instruct.Q2_K"
url: "https://huggingface.co/mozilla-ai/Meta-Llama-3-70B-Instruct-llamafile/resolve/main/Meta-Llama-3-70B-Instruct.Q2_K.llamafile"
quantization: "Q2_K"
size_bytes: 26405321096
llama_version: "3"
params: "70B"
downloads: 232
pipeline_tag: "text-generation"
filename: "Meta-Llama-3-70B-Instruct.Q2_K.llamafile"
repo: "mozilla-ai/Meta-Llama-3-70B-Instruct-llamafile"
- alias: "llama3:70b-q3"
description: "Meta-Llama-3-70B-Instruct.Q3_K_M"
url: "https://huggingface.co/mozilla-ai/Meta-Llama-3-70B-Instruct-llamafile/resolve/main/Meta-Llama-3-70B-Instruct.Q3_K_M.llamafile"
quantization: "Q3_K_M"
size_bytes: 34297690508
llama_version: "3"
params: "70B"
downloads: 232
pipeline_tag: "text-generation"
filename: "Meta-Llama-3-70B-Instruct.Q3_K_M.llamafile"
repo: "mozilla-ai/Meta-Llama-3-70B-Instruct-llamafile"
- alias: "llama3:70b-q5"
description: "Meta-Llama-3-70B-Instruct.Q5_K_M"
url: "https://huggingface.co/mozilla-ai/Meta-Llama-3-70B-Instruct-llamafile/resolve/main/Meta-Llama-3-70B-Instruct.Q5_K_M.llamafile"
quantization: "Q5_K_M"
size_bytes: 49979210025
llama_version: "3"
params: "70B"
downloads: 232
pipeline_tag: "text-generation"
filename: "Meta-Llama-3-70B-Instruct.Q5_K_M.llamafile"
repo: "mozilla-ai/Meta-Llama-3-70B-Instruct-llamafile"
- alias: "gemma2:27b"
description: "gemma-2-27b-it.Q4_K_M"
url: "https://huggingface.co/mozilla-ai/gemma-2-27b-it-llamafile/resolve/main/gemma-2-27b-it.Q4_K_M.llamafile"
quantization: "Q4_K_M"
size_bytes: 16815241375
llama_version: "2"
params: "27B"
downloads: 229
pipeline_tag: ""
filename: "gemma-2-27b-it.Q4_K_M.llamafile"
repo: "mozilla-ai/gemma-2-27b-it-llamafile"
- alias: "gemma2:27b-q4"
description: "gemma-2-27b-it.Q4_K_M"
url: "https://huggingface.co/mozilla-ai/gemma-2-27b-it-llamafile/resolve/main/gemma-2-27b-it.Q4_K_M.llamafile"
quantization: "Q4_K_M"
size_bytes: 16815241375
llama_version: "2"
params: "27B"
downloads: 229
pipeline_tag: ""
filename: "gemma-2-27b-it.Q4_K_M.llamafile"
repo: "mozilla-ai/gemma-2-27b-it-llamafile"
- alias: "gemma2:27b-q2"
description: "gemma-2-27b-it.Q2_K"
url: "https://huggingface.co/mozilla-ai/gemma-2-27b-it-llamafile/resolve/main/gemma-2-27b-it.Q2_K.llamafile"
quantization: "Q2_K"
size_bytes: 10619402395
llama_version: "2"
params: "27B"
downloads: 229
pipeline_tag: ""
filename: "gemma-2-27b-it.Q2_K.llamafile"
repo: "mozilla-ai/gemma-2-27b-it-llamafile"
- alias: "gemma2:27b-q3"
description: "gemma-2-27b-it.Q3_K_M"
url: "https://huggingface.co/mozilla-ai/gemma-2-27b-it-llamafile/resolve/main/gemma-2-27b-it.Q3_K_M.llamafile"
quantization: "Q3_K_M"
size_bytes: 13594474655
llama_version: "2"
params: "27B"
downloads: 229
pipeline_tag: ""
filename: "gemma-2-27b-it.Q3_K_M.llamafile"
repo: "mozilla-ai/gemma-2-27b-it-llamafile"
- alias: "gemma2:27b-q5"
description: "gemma-2-27b-it.Q5_K_M"
url: "https://huggingface.co/mozilla-ai/gemma-2-27b-it-llamafile/resolve/main/gemma-2-27b-it.Q5_K_M.llamafile"
quantization: "Q5_K_M"
size_bytes: 19577976991
llama_version: "2"
params: "27B"
downloads: 229
pipeline_tag: ""
filename: "gemma-2-27b-it.Q5_K_M.llamafile"
repo: "mozilla-ai/gemma-2-27b-it-llamafile"
- alias: "gemma2:27b-q6"
description: "gemma-2-27b-it.Q6_K"
url: "https://huggingface.co/mozilla-ai/gemma-2-27b-it-llamafile/resolve/main/gemma-2-27b-it.Q6_K.llamafile"
quantization: "Q6_K"
size_bytes: 22513399963
llama_version: "2"
params: "27B"
downloads: 229
pipeline_tag: ""
filename: "gemma-2-27b-it.Q6_K.llamafile"
repo: "mozilla-ai/gemma-2-27b-it-llamafile"
- alias: "gemma2:27b-q8"
description: "gemma-2-27b-it.Q8_0"
url: "https://huggingface.co/mozilla-ai/gemma-2-27b-it-llamafile/resolve/main/gemma-2-27b-it.Q8_0.llamafile"
quantization: "Q8_0"
size_bytes: 29107239067
llama_version: "2"
params: "27B"
downloads: 229
pipeline_tag: ""
filename: "gemma-2-27b-it.Q8_0.llamafile"
repo: "mozilla-ai/gemma-2-27b-it-llamafile"
- alias: "granite34:34b"
description: "granite-34b-code-instruct.Q5_0"
url: "https://huggingface.co/mozilla-ai/granite-34b-code-instruct-llamafile/resolve/main/granite-34b-code-instruct.Q5_0.llamafile"
quantization: "Q5_0"
size_bytes: 23433656503
llama_version: "34"
params: "34B"
downloads: 210
pipeline_tag: "text-generation"
filename: "granite-34b-code-instruct.Q5_0.llamafile"
repo: "mozilla-ai/granite-34b-code-instruct-llamafile"
- alias: "granite34:34b-q5"
description: "granite-34b-code-instruct.Q5_0"
url: "https://huggingface.co/mozilla-ai/granite-34b-code-instruct-llamafile/resolve/main/granite-34b-code-instruct.Q5_0.llamafile"
quantization: "Q5_0"
size_bytes: 23433656503
llama_version: "34"
params: "34B"
downloads: 210
pipeline_tag: "text-generation"
filename: "granite-34b-code-instruct.Q5_0.llamafile"
repo: "mozilla-ai/granite-34b-code-instruct-llamafile"
- alias: "granite34:34b-q8"
description: "granite-34b-code-instruct.Q8_0"
url: "https://huggingface.co/mozilla-ai/granite-34b-code-instruct-llamafile/resolve/main/granite-34b-code-instruct.Q8_0.llamafile"
quantization: "Q8_0"
size_bytes: 36015782071
llama_version: "34"
params: "34B"
downloads: 210
pipeline_tag: "text-generation"
filename: "granite-34b-code-instruct.Q8_0.llamafile"
repo: "mozilla-ai/granite-34b-code-instruct-llamafile"
- alias: "qwen2.5:7b"
description: "Qwen2.5.1-Coder-7B-Instruct-Q4_K_M"
url: "https://huggingface.co/mozilla-ai/Qwen2.5.1-Coder-7B-Instruct-llamafile/resolve/main/Qwen2.5.1-Coder-7B-Instruct-Q4_K_M.llamafile"
quantization: "Q4_K_M"
size_bytes: 4990851113
llama_version: "2.5"
params: "7B"
downloads: 158
pipeline_tag: "text-generation"
filename: "Qwen2.5.1-Coder-7B-Instruct-Q4_K_M.llamafile"
repo: "mozilla-ai/Qwen2.5.1-Coder-7B-Instruct-llamafile"
- alias: "qwen2.5:7b-q4"
description: "Qwen2.5.1-Coder-7B-Instruct-Q4_K_M"
url: "https://huggingface.co/mozilla-ai/Qwen2.5.1-Coder-7B-Instruct-llamafile/resolve/main/Qwen2.5.1-Coder-7B-Instruct-Q4_K_M.llamafile"
quantization: "Q4_K_M"
size_bytes: 4990851113
llama_version: "2.5"
params: "7B"
downloads: 158
pipeline_tag: "text-generation"
filename: "Qwen2.5.1-Coder-7B-Instruct-Q4_K_M.llamafile"
repo: "mozilla-ai/Qwen2.5.1-Coder-7B-Instruct-llamafile"
- alias: "qwen2.5:7b-q5"
description: "Qwen2.5.1-Coder-7B-Instruct-Q5_K_M"
url: "https://huggingface.co/mozilla-ai/Qwen2.5.1-Coder-7B-Instruct-llamafile/resolve/main/Qwen2.5.1-Coder-7B-Instruct-Q5_K_M.llamafile"
quantization: "Q5_K_M"
size_bytes: 5752576041
llama_version: "2.5"
params: "7B"
downloads: 158
pipeline_tag: "text-generation"
filename: "Qwen2.5.1-Coder-7B-Instruct-Q5_K_M.llamafile"
repo: "mozilla-ai/Qwen2.5.1-Coder-7B-Instruct-llamafile"
- alias: "qwen2.5:7b-q6"
description: "Qwen2.5.1-Coder-7B-Instruct-Q6_K"
url: "https://huggingface.co/mozilla-ai/Qwen2.5.1-Coder-7B-Instruct-llamafile/resolve/main/Qwen2.5.1-Coder-7B-Instruct-Q6_K.llamafile"
quantization: "Q6_K"
size_bytes: 6561945637
llama_version: "2.5"
params: "7B"
downloads: 158
pipeline_tag: "text-generation"
filename: "Qwen2.5.1-Coder-7B-Instruct-Q6_K.llamafile"
repo: "mozilla-ai/Qwen2.5.1-Coder-7B-Instruct-llamafile"
- alias: "qwen2.5:7b-q8"
description: "Qwen2.5.1-Coder-7B-Instruct-Q8_0"
url: "https://huggingface.co/mozilla-ai/Qwen2.5.1-Coder-7B-Instruct-llamafile/resolve/main/Qwen2.5.1-Coder-7B-Instruct-Q8_0.llamafile"
quantization: "Q8_0"
size_bytes: 8406259749
llama_version: "2.5"
params: "7B"
downloads: 158
pipeline_tag: "text-generation"
filename: "Qwen2.5.1-Coder-7B-Instruct-Q8_0.llamafile"
repo: "mozilla-ai/Qwen2.5.1-Coder-7B-Instruct-llamafile"
- alias: "qwen2.5:0.5b"
description: "Qwen2.5-0.5B-Instruct-Q4_K_M"
url: "https://huggingface.co/mozilla-ai/Qwen2.5-0.5B-Instruct-llamafile/resolve/main/Qwen2.5-0.5B-Instruct-Q4_K_M.llamafile"
quantization: "Q4_K_M"
size_bytes: 705583133
llama_version: "2.5"
params: "0.5B"
downloads: 140
pipeline_tag: "text-generation"
filename: "Qwen2.5-0.5B-Instruct-Q4_K_M.llamafile"
repo: "mozilla-ai/Qwen2.5-0.5B-Instruct-llamafile"
- alias: "qwen2.5:0.5b-q4"
description: "Qwen2.5-0.5B-Instruct-Q4_K_M"
url: "https://huggingface.co/mozilla-ai/Qwen2.5-0.5B-Instruct-llamafile/resolve/main/Qwen2.5-0.5B-Instruct-Q4_K_M.llamafile"
quantization: "Q4_K_M"
size_bytes: 705583133
llama_version: "2.5"
params: "0.5B"
downloads: 140
pipeline_tag: "text-generation"
filename: "Qwen2.5-0.5B-Instruct-Q4_K_M.llamafile"
repo: "mozilla-ai/Qwen2.5-0.5B-Instruct-llamafile"
- alias: "qwen2.5:0.5b-q5"
description: "Qwen2.5-0.5B-Instruct-Q5_K_M"
url: "https://huggingface.co/mozilla-ai/Qwen2.5-0.5B-Instruct-llamafile/resolve/main/Qwen2.5-0.5B-Instruct-Q5_K_M.llamafile"
quantization: "Q5_K_M"
size_bytes: 727865373
llama_version: "2.5"
params: "0.5B"
downloads: 140
pipeline_tag: "text-generation"
filename: "Qwen2.5-0.5B-Instruct-Q5_K_M.llamafile"
repo: "mozilla-ai/Qwen2.5-0.5B-Instruct-llamafile"
- alias: "qwen2.5:0.5b-q6"
description: "Qwen2.5-0.5B-Instruct-Q6_K"
url: "https://huggingface.co/mozilla-ai/Qwen2.5-0.5B-Instruct-llamafile/resolve/main/Qwen2.5-0.5B-Instruct-Q6_K.llamafile"
quantization: "Q6_K"
size_bytes: 813455385
llama_version: "2.5"
params: "0.5B"
downloads: 140
pipeline_tag: "text-generation"
filename: "Qwen2.5-0.5B-Instruct-Q6_K.llamafile"
repo: "mozilla-ai/Qwen2.5-0.5B-Instruct-llamafile"
- alias: "qwen2.5:0.5b-q8"
description: "Qwen2.5-0.5B-Instruct-Q8_0"
url: "https://huggingface.co/mozilla-ai/Qwen2.5-0.5B-Instruct-llamafile/resolve/main/Qwen2.5-0.5B-Instruct-Q8_0.llamafile"
quantization: "Q8_0"
size_bytes: 838817817
llama_version: "2.5"
params: "0.5B"
downloads: 140
pipeline_tag: "text-generation"
filename: "Qwen2.5-0.5B-Instruct-Q8_0.llamafile"
repo: "mozilla-ai/Qwen2.5-0.5B-Instruct-llamafile"
Versions
| Version | Published | Status |
|---|---|---|
| 1.0.5 | 10/14/2026 | active |
| 1.0.4 | 10/13/2026 | active |
| 1.0.3 | 10/12/2026 | active |
| 1.0.2 | 10/11/2026 | active |
Details
- Author
- kdeps
- License
- Apache-2.0
- Latest Version
- 1.0.5
- Published
- 10/11/2026
Tags
kdepsmodel