Non-uniform GGUF quantizations via GSQ + RCO: per-tensor mixed precision in standard GGUF form
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
Hardware-Native Joint Sparse-Quantization for Trillion-Scale Mixture-of-Experts
WUSH-KV: KV Cache Quantization with Data-Adaptive Transforms
Paired-4:8 + NVFP4 W4A4 expert compressed MoE models for NVIDIA Blackwell Sparse Tensor Cores.
-
ISTA-DASLab/Kimi-K2.5-P48NVFP4-MoESQ
Text Generation • 646B • Updated • 621 • 1 -
ISTA-DASLab/Qwen3-30B-A3B-P48NVFP4-MoESQ
Text Generation • 20B • Updated • 861 • 3 -
ISTA-DASLab/Qwen3.5-397B-A17B-P48NVFP4-MoESQ
Image-Text-to-Text • 258B • Updated • 79 • 1 -
ISTA-DASLab/Qwen3.8-Flash-Next-P48NVFP4-MoESQ
Text Generation • 135B • Updated • 1.14k • 12
Non-uniform GGUF quantizations via GSQ + RCO: per-tensor mixed precision in standard GGUF form
Paired-4:8 + NVFP4 W4A4 expert compressed MoE models for NVIDIA Blackwell Sparse Tensor Cores.
-
ISTA-DASLab/Kimi-K2.5-P48NVFP4-MoESQ
Text Generation • 646B • Updated • 621 • 1 -
ISTA-DASLab/Qwen3-30B-A3B-P48NVFP4-MoESQ
Text Generation • 20B • Updated • 861 • 3 -
ISTA-DASLab/Qwen3.5-397B-A17B-P48NVFP4-MoESQ
Image-Text-to-Text • 258B • Updated • 79 • 1 -
ISTA-DASLab/Qwen3.8-Flash-Next-P48NVFP4-MoESQ
Text Generation • 135B • Updated • 1.14k • 12
models 143
ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF
Text Generation • 197B • Updated • 67
ISTA-DASLab/Qwen3-8B-MatGPTQ
Text Generation • 8B • Updated • 130 • 3
ISTA-DASLab/Llama-3.1-8B-Instruct-MatGPTQ
Text Generation • 8B • Updated • 184
ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF
Image-Text-to-Text • 117B • Updated • 938k • 483
ISTA-DASLab/Kimi-K3-P48NVFP4-MoESQ
Text Generation • Updated • 341 • 3
ISTA-DASLab/Qwen3.8-Flash-Next-P48NVFP4-MoESQ
Text Generation • 135B • Updated • 1.14k • 12
ISTA-DASLab/Qwen3.5-397B-A17B-P48NVFP4-MoESQ
Image-Text-to-Text • 258B • Updated • 79 • 1
ISTA-DASLab/Qwen3-30B-A3B-P48NVFP4-MoESQ
Text Generation • 20B • Updated • 861 • 3
ISTA-DASLab/Kimi-K2.5-P48NVFP4-MoESQ
Text Generation • 646B • Updated • 621 • 1
ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF
Image-Text-to-Text • 177B • Updated • 6.51M • 1k