inference-optimization/ctest-subset-Qwen3.5-397B-A17B-FP8-dynamic-speculator-dataset Viewer • Updated about 5 hours ago • 10k
inference-optimization/ctest-subset-Qwen3.5-397B-A17B-FP8-dynamic-speculator-dataset Viewer • Updated about 5 hours ago • 10k
inference-optimization/Qwen3-235B-A22B-Thinking-2507.w8a8 Text Generation • 235B • Updated 3 days ago • 128
inference-optimization/Qwen3-235B-A22B-Thinking-2507.w4a16 Text Generation • 32B • Updated 3 days ago • 108
inference-optimization/final-ctest-Qwen3-8B-speculator-dataset Viewer • Updated 5 days ago • 10k • 35
inference-optimization/final-ctest-Qwen3-8B-speculator-dataset Viewer • Updated 5 days ago • 10k • 35
HIGGS-stiched Collection Stitched HIGGS Llama3 8B mixed-precision model variants. • 36 items • Updated 7 days ago