ISTA-DASLab/Kimi-K2.5-P48NVFP4-MoESQ
Text Generation • 646B • Updated
MoESQ
Paired-4:8 + NVFP4 W4A4 expert compressed MoE models for NVIDIA Blackwell Sparse Tensor Cores.
Paired-4:8 + NVFP4 W4A4 expert compressed MoE models for NVIDIA Blackwell Sparse Tensor Cores.