Hugging Face's logo

VibeStudio
/
MiniMax-M2-THRIFT-55-MLX-4bit

MLX
Safetensors
minimax
Mixture of Experts
bfloat16
sglang
custom_code
4-bit precision
Model card Files
xet
Community
1
New discussion

Could you please quantize a 6-bit or 6.5-bit model that requires 93-97GB of memory? Such a model could be deployed on a Mac with 128GB of RAM. Thank you very much!
#1 opened 5 days ago by
mimeng1990