tensorblock/AceGPT-v2-70B-Chat-GGUF

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

FreedomIntelligence/AceGPT-v2-70B-Chat - GGUF

This repo contains GGUF format model files for FreedomIntelligence/AceGPT-v2-70B-Chat.

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
AceGPT-v2-70B-Chat-Q2_K.gguf	Q2_K	26.375 GB	smallest, significant quality loss - not recommended for most purposes
AceGPT-v2-70B-Chat-Q3_K_S.gguf	Q3_K_S	30.912 GB	very small, high quality loss
AceGPT-v2-70B-Chat-Q3_K_M.gguf	Q3_K_M	34.267 GB	very small, high quality loss
AceGPT-v2-70B-Chat-Q3_K_L.gguf	Q3_K_L	37.141 GB	small, substantial quality loss
AceGPT-v2-70B-Chat-Q4_0.gguf	Q4_0	39.970 GB	legacy; small, very high quality loss - prefer using Q3_K_M
AceGPT-v2-70B-Chat-Q4_K_S.gguf	Q4_K_S	40.347 GB	small, greater quality loss
AceGPT-v2-70B-Chat-Q4_K_M.gguf	Q4_K_M	42.520 GB	medium, balanced quality - recommended
AceGPT-v2-70B-Chat-Q5_0.gguf	Q5_0	48.657 GB	legacy; medium, balanced quality - prefer using Q4_K_M
AceGPT-v2-70B-Chat-Q5_K_S.gguf	Q5_K_S	48.657 GB	large, low quality loss - recommended
AceGPT-v2-70B-Chat-Q5_K_M.gguf	Q5_K_M	49.950 GB	large, very low quality loss - recommended
AceGPT-v2-70B-Chat-Q6_K	Q6_K	57.888 GB	very large, extremely low quality loss
AceGPT-v2-70B-Chat-Q8_0	Q8_0	74.975 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/AceGPT-v2-70B-Chat-GGUF --include "AceGPT-v2-70B-Chat-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/AceGPT-v2-70B-Chat-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'