Hugging Face's logo

daslab-testing
/
Llama-3.3-70B-Instruct-mxfp-w4-a4-GPTQ-hadamard-transform

Safetensors
llama
8-bit precision
fp_quant
Model card Files
xet
Community
Llama-3.3-70B-Instruct-mxfp-w4-a4-GPTQ-hadamard-transform / model-6-of-8.safetensors

Commit History

Upload folder using huggingface_hub
0b47046
verified

SpiridonSunRotator commited on