Intel and MiniMax Release MXFP4 Quantized Model, Topping FP4 Benchmarks

HaihaoShen · x · 2026-08-14

Intel has partnered with @MiniMaxAI to release the MiniMax-M3-MXFP4 model, achieving SOTA FP4 performance on benchmarks.

The release includes the AutoRound quantization tool and a detailed technical blog post. Model weights are now available on Hugging Face.

Original post →

More from Infra

Infra channel →