vLLM container (and instructions) to run this on SM120 forthcoming - until then it may be difficult to run this due to the specialized kernels required.

Downloads last month
485
Safetensors
Model size
246B params
Tensor type
BF16
·
F8_E4M3
·
U8
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for lukealonso/MiniMax-M3-NVFP4

Quantized
(17)
this model