Firworks
/

INTELLECT-3-nvfp4

8-bit precision

compressed-tensors

Model card Files Files and versions

Resources

View closed (1)

Request quantization model

#6 opened 23 days ago by

cost estimates?

#5 opened 23 days ago by

is NVFP4 supported on sm120 (blackwell rtx pro 6000, rtx 5090 etc)?

#4 opened 24 days ago by

Minimax

#3 opened 25 days ago by

works with vLLM, with FLASHINFER_MOE_FP4

#2 opened 27 days ago by

Can you redece the size from 62 GB to about 35-40 GB range in 4bit or lesser?

#1 opened 27 days ago by