tensorblock/magnum-v4-22b-GGUF

Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server

anthracite-org/magnum-v4-22b - GGUF

This repo contains GGUF format model files for anthracite-org/magnum-v4-22b.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.

<s>[INST] {system_prompt}

{prompt}[/INST]

Filename	Quant type	File Size	Description
magnum-v4-22b-Q2_K.gguf	Q2_K	8.272 GB	smallest, significant quality loss - not recommended for most purposes
magnum-v4-22b-Q3_K_S.gguf	Q3_K_S	9.641 GB	very small, high quality loss
magnum-v4-22b-Q3_K_M.gguf	Q3_K_M	10.757 GB	very small, high quality loss
magnum-v4-22b-Q3_K_L.gguf	Q3_K_L	11.730 GB	small, substantial quality loss
magnum-v4-22b-Q4_0.gguf	Q4_0	12.569 GB	legacy; small, very high quality loss - prefer using Q3_K_M
magnum-v4-22b-Q4_K_S.gguf	Q4_K_S	12.660 GB	small, greater quality loss
magnum-v4-22b-Q4_K_M.gguf	Q4_K_M	13.341 GB	medium, balanced quality - recommended
magnum-v4-22b-Q5_0.gguf	Q5_0	15.325 GB	legacy; medium, balanced quality - prefer using Q4_K_M
magnum-v4-22b-Q5_K_S.gguf	Q5_K_S	15.325 GB	large, low quality loss - recommended
magnum-v4-22b-Q5_K_M.gguf	Q5_K_M	15.723 GB	large, very low quality loss - recommended
magnum-v4-22b-Q6_K.gguf	Q6_K	18.253 GB	very large, extremely low quality loss
magnum-v4-22b-Q8_0.gguf	Q8_0	23.641 GB	very large, extremely low quality loss - not recommended

Firstly, install Huggingface Client

pip install -U "huggingface_hub[cli]"

Then, downoad the individual model file the a local directory

huggingface-cli download tensorblock/magnum-v4-22b-GGUF --include "magnum-v4-22b-Q2_K.gguf" --local-dir MY_LOCAL_DIR

If you wanna download multiple model files with a pattern (e.g., *Q4_K*gguf), you can try:

huggingface-cli download tensorblock/magnum-v4-22b-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'