Hugging Face's logo

baa-ai
/
MiniMax-M2.7-RAM-111GB-MLX

Text Generation
MLX
Safetensors
English
minimax_m2
quantized
mixed-precision
minimax
Mixture of Experts
conversational
custom_code
4-bit precision
Model card Files
xet
 Community
MiniMax-M2.7-RAM-111GB-MLX / tokenizer.json

Commit History

Initial upload: MiniMax-M2.7 mixed-precision MLX (111 GB)
22f8592
verified

tomkay commited on