Hugging Face's logo

baa-ai
/
MiniMax-M2.5-RAM-120GB-MLX

MLX
Safetensors
minimax_m2
quantized
mixed-precision
minimax
Mixture of Experts
custom_code
4-bit precision
Model card Files
xet
 Community
MiniMax-M2.5-RAM-120GB-MLX / tokenizer.json

Commit History

RAM 120GB mixed-precision quantization of MiniMax-M2.5
f3940f8
verified

tomkay commited on