Using llama.cpp release b5223 for quantization. Original model: https://huggingface.co/unsloth/Devstral-Small-2505 Run them directly with llama.cpp, or any other llama.cpp based project

Prompt format

<｜begin▁of▁sentence｜>{system_prompt}<｜User｜>{prompt}<｜Assistant｜><｜end▁of▁sentence｜><｜Assistant｜>

Download a file (not the whole branch) from below:

Filename	Quant type	File Size	Split
devstral-small-2505-q2_k.gguf	Q2_K	8.28 GB	False
devstral-small-2505-q3_k_l.gguf	Q3_K_L	11.55 GB	False
devstral-small-2505-q6_k.gguf	Q6_K	18.02 GB	False
devstral-small-2505-q4_k_m.gguf	Q4_K_M	13.35 GB	False
devstral-small-2505-q5_k_m.gguf	Q5_K_M	15.61 GB	False
devstral-small-2505-q8_0.gguf	Q8_0	23.33 GB	False

Click to view download instructions

First, make sure you have hugginface-cli installed:

pip install -U "huggingface_hub[cli]"

Then, you can target the specific file you want:

huggingface-cli download https://huggingface.co/Antigma/Devstral-Small-2505-GGUF --include "devstral-small-2505-q2_k.gguf" --local-dir ./

If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run:

huggingface-cli download https://huggingface.co/Antigma/Devstral-Small-2505-GGUF --include "devstral-small-2505-q2_k.gguf/*" --local-dir ./

You can either specify a new local-dir (deepseek-ai_DeepSeek-V3-0324-Q8_0) or download them all in place (./)