ISTA-DASLab/Kimi-K2.5-P48NVFP4-MoESQ
Text Generation • 646B • Updated • 565 • 3
MoESQ
Paired-4:8 + NVFP4 W4A4 expert compressed MoE models for NVIDIA Blackwell Sparse Tensor Cores.
-
-
ISTA-DASLab/Qwen3-30B-A3B-P48NVFP4-MoESQ
Text Generation • 20B • Updated • 860 • 7 -
ISTA-DASLab/Qwen3.5-397B-A17B-P48NVFP4-MoESQ
Image-Text-to-Text • 258B • Updated • 73 • 2 -
ISTA-DASLab/Qwen3.8-Flash-Next-P48NVFP4-MoESQ
Text Generation • 135B • Updated • 1.2k • 14 -
Hardware-Native Joint Sparse-Quantization for Trillion-Scale Mixture-of-Experts
Paper • 2610.02241 • Published • 7 -
ISTA-DASLab/Kimi-K3-P48NVFP4-MoESQ
Text Generation • Updated • 416 • 4