lukealonso
/

MiniMax-M2.7-NVFP4

8-bit precision

Model card Files Files and versions

Resources

View closed (0)

Working VLLM Command

#10 opened 25 days ago by

Unable to use full 192k context in SGLang with MiniMax-M2.7-NVFP4 (runtime capped at ~80,964 tokens)

#9 opened about 1 month ago by

"KLD reduced by ~10%."

#8 opened about 1 month ago by

Next-level!

#7 opened about 1 month ago by

2 DGX Spark cluster recipe

#6 opened about 2 months ago by

tokenizer component mismatch and w1_weight_scale_2 must match w3_weight_scale_2. Accuracy may be affected issue

#5 opened about 2 months ago by

Working configuration for Nvidia Blackwell

#4 opened about 2 months ago by

Calibration Dataset Mixture

#3 opened about 2 months ago by

Thanks, thanks and more thanks. Many thanks.

#2 opened about 2 months ago by

w1 not matching w3 weight scales

#1 opened about 2 months ago by