Hugging Face's logo

baa-ai
/
Llama-3.3-70B-Instruct-RAM-50GB-MLX

MLX
Safetensors
llama
quantized
mixed-precision
4-bit precision
Model card Files
xet
 Community
Llama-3.3-70B-Instruct-RAM-50GB-MLX / chat_template.jinja

Commit History

RAM 50GB mixed-precision quantization of Llama-3.3-70B-Instruct
847621f
verified

tomkay commited on