tensorblock/CodeLlama-34b-hf-GGUF

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

meta-llama/CodeLlama-34b-hf - GGUF

This repo contains GGUF format model files for meta-llama/CodeLlama-34b-hf.

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

Filename	Quant type	File Size	Description
CodeLlama-34b-hf-Q2_K.gguf	Q2_K	12.506 GB	smallest, significant quality loss - not recommended for most purposes
CodeLlama-34b-hf-Q3_K_S.gguf	Q3_K_S	14.605 GB	very small, high quality loss
CodeLlama-34b-hf-Q3_K_M.gguf	Q3_K_M	16.306 GB	very small, high quality loss
CodeLlama-34b-hf-Q3_K_L.gguf	Q3_K_L	17.772 GB	small, substantial quality loss
CodeLlama-34b-hf-Q4_0.gguf	Q4_0	19.052 GB	legacy; small, very high quality loss - prefer using Q3_K_M
CodeLlama-34b-hf-Q4_K_S.gguf	Q4_K_S	19.192 GB	small, greater quality loss
CodeLlama-34b-hf-Q4_K_M.gguf	Q4_K_M	20.220 GB	medium, balanced quality - recommended
CodeLlama-34b-hf-Q5_0.gguf	Q5_0	23.237 GB	legacy; medium, balanced quality - prefer using Q4_K_M
CodeLlama-34b-hf-Q5_K_S.gguf	Q5_K_S	23.237 GB	large, low quality loss - recommended
CodeLlama-34b-hf-Q5_K_M.gguf	Q5_K_M	23.839 GB	large, very low quality loss - recommended
CodeLlama-34b-hf-Q6_K.gguf	Q6_K	27.684 GB	very large, extremely low quality loss
CodeLlama-34b-hf-Q8_0.gguf	Q8_0	35.856 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-34b-hf-GGUF --include "CodeLlama-34b-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-34b-hf-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'