tensorblock/CodeLlama-70b-hf-GGUF

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

codellama/CodeLlama-70b-hf - GGUF

This repo contains GGUF format model files for codellama/CodeLlama-70b-hf.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4242.

Filename	Quant type	File Size	Description
CodeLlama-70b-hf-Q2_K.gguf	Q2_K	25.463 GB	smallest, significant quality loss - not recommended for most purposes
CodeLlama-70b-hf-Q3_K_S.gguf	Q3_K_S	29.919 GB	very small, high quality loss
CodeLlama-70b-hf-Q3_K_M.gguf	Q3_K_M	33.275 GB	very small, high quality loss
CodeLlama-70b-hf-Q3_K_L.gguf	Q3_K_L	36.148 GB	small, substantial quality loss
CodeLlama-70b-hf-Q4_0.gguf	Q4_0	38.872 GB	legacy; small, very high quality loss - prefer using Q3_K_M
CodeLlama-70b-hf-Q4_K_S.gguf	Q4_K_S	39.250 GB	small, greater quality loss
CodeLlama-70b-hf-Q4_K_M.gguf	Q4_K_M	41.423 GB	medium, balanced quality - recommended
CodeLlama-70b-hf-Q5_0.gguf	Q5_0	47.462 GB	legacy; medium, balanced quality - prefer using Q4_K_M
CodeLlama-70b-hf-Q5_K_S.gguf	Q5_K_S	47.462 GB	large, low quality loss - recommended
CodeLlama-70b-hf-Q5_K_M.gguf	Q5_K_M	48.754 GB	large, very low quality loss - recommended
CodeLlama-70b-hf-Q6_K	Q6_K	56.588 GB	very large, extremely low quality loss
CodeLlama-70b-hf-Q8_0	Q8_0	73.293 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/CodeLlama-70b-hf-GGUF --include "CodeLlama-70b-hf-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/CodeLlama-70b-hf-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'