Hugging Face's logo

mlx-community
/
MiniMax-M2.1-3bit

Text Generation
MLX
Safetensors
Transformers
minimax
conversational
custom_code
3-bit
Model card Files
xet
Community
1
New discussion

Anyone running this with M4 Max 128gb? How does it compare to 4bit quantization?

1
#1 opened about 11 hours ago by
tumma72