tensorblock/Llama-2-7B-Chat-fp16-GGUF

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

TheBloke/Llama-2-7B-Chat-fp16 - GGUF

This repo contains GGUF format model files for TheBloke/Llama-2-7B-Chat-fp16.

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
Llama-2-7B-Chat-fp16-Q2_K.gguf	Q2_K	2.359 GB	smallest, significant quality loss - not recommended for most purposes
Llama-2-7B-Chat-fp16-Q3_K_S.gguf	Q3_K_S	2.746 GB	very small, high quality loss
Llama-2-7B-Chat-fp16-Q3_K_M.gguf	Q3_K_M	3.072 GB	very small, high quality loss
Llama-2-7B-Chat-fp16-Q3_K_L.gguf	Q3_K_L	3.350 GB	small, substantial quality loss
Llama-2-7B-Chat-fp16-Q4_0.gguf	Q4_0	3.563 GB	legacy; small, very high quality loss - prefer using Q3_K_M
Llama-2-7B-Chat-fp16-Q4_K_S.gguf	Q4_K_S	3.592 GB	small, greater quality loss
Llama-2-7B-Chat-fp16-Q4_K_M.gguf	Q4_K_M	3.801 GB	medium, balanced quality - recommended
Llama-2-7B-Chat-fp16-Q5_0.gguf	Q5_0	4.332 GB	legacy; medium, balanced quality - prefer using Q4_K_M
Llama-2-7B-Chat-fp16-Q5_K_S.gguf	Q5_K_S	4.332 GB	large, low quality loss - recommended
Llama-2-7B-Chat-fp16-Q5_K_M.gguf	Q5_K_M	4.455 GB	large, very low quality loss - recommended
Llama-2-7B-Chat-fp16-Q6_K.gguf	Q6_K	5.149 GB	very large, extremely low quality loss
Llama-2-7B-Chat-fp16-Q8_0.gguf	Q8_0	6.669 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/Llama-2-7B-Chat-fp16-GGUF --include "Llama-2-7B-Chat-fp16-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/Llama-2-7B-Chat-fp16-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'