Hugging Face's logo

nvidia
/
MiniMax-M2.5-NVFP4

Text Generation
Safetensors
Model Optimizer
minimax_m2
nvidia
ModelOpt
MiniMax
quantized
NVFP4
nvfp4
conversational
custom_code
8-bit precision
modelopt
Model card Files
xet
 Community
4
MiniMax-M2.5-NVFP4
140 GB
  • 2 contributors
 History: 4 commits
wangshangsam's picture
wangshangsam
Add vLLM as one of the supported inference engines.
8067802 verified