Models with expert pruning applied
-
inference-optimization/GLM-5.3-Flash-NVFP4-RAZOR20
Image-Text-to-Text • 138B • Updated • 25 -
inference-optimization/Qwen3.6-35B-A3B-RAZOR25
Image-Text-to-Text • 28B • Updated • 30 -
inference-optimization/Qwen3-30B-A3B-RAZOR20
Text Generation • 25B • Updated • 378 -
inference-optimization/Qwen3-30B-A3B-Instruct-2507-MoNe-25
23B • Updated • 21