inference-optimization/DeepSeek-V4-2.7B-tiny
3B • Updated • 34
Inference Optimization
community
AI & ML interests
None defined yet.
Recent Activity
inference-optimization/Qwen3-8B-speculator.dflash.swa.causal-qwen235b-instruct-bs16-muon-ckpt6
2B • Updated • 9
inference-optimization/GLM-5.2-0.8B-A0.8B
Text Generation • 0.8B • Updated • 4.16k • 4
inference-optimization/Qwen3-8B-speculator.dflash.swa.causal-qwen235b-instruct-bs16-muon-ckpt5
2B • Updated • 7
inference-optimization/Qwen3-8B-speculator.dflash.swa.non-qwen3-step420136
2B • Updated • 9
inference-optimization/Qwen3-8B-speculator.dflash.swa.causal-qwen235b-instruct-bs16-muon-ckpt4
2B • Updated • 9
inference-optimization/Qwen3-8B-FP8-Dynamic
Text Generation • 8B • Updated • 6
inference-optimization/Qwen3-8B-speculator.dflash.fullattn-qwen235b-instruct-bs16-ckpt0
2B • Updated • 7
inference-optimization/dflash-DeepSeek-V4-Flash-all-swa-muon-speculators-50k
2B • Updated • 46 • 2
inference-optimization/Qwen3.5-397B-A17B-FP8-dynamic-data-subset-speculator.dflash
2B • Updated • 12
inference-optimization/Qwen3-8B-from-Qwen3-8B_regen-speculators.eagle31-fcnorm-ckpt1
1B • Updated • 13
inference-optimization/Qwen3-8B-speculator.dflash.swa.causal-qwen235b-instruct-bs16-ckpt4
2B • Updated • 12
inference-optimization/Qwen3-8B-from-Qwen3-8B_regen-speculators.eagle31-qwen3arch-3e4-ckpt1
1B • Updated • 9
inference-optimization/Qwen3-8B-speculator.dflash.swa.causal-qwen235b-instruct-bs16-ckpt3
2B • Updated • 8
inference-optimization/Qwen3-8B-from-Qwen3-8B_regen-speculators.eagle31-qwen3arch-ckpt1
1B • Updated • 15
inference-optimization/Nemotron-3-Super-prepared-data
Updated
inference-optimization/Nemotron-Super-120B-Dflash-SWA
1B • Updated • 8
inference-optimization/Qwen3-8B-speculator.dflash.swa.non-qwen3-step210040
2B • Updated • 8
inference-optimization/Qwen3-8B-speculator.dflash.swa.causal-qwen235b-instruct-bs16-ckpt2
2B • Updated • 11
inference-optimization/Phi-3.5-MoE-0.8B-A0.2B
Text Generation • 0.8B • Updated • 10
inference-optimization/Qwen3-8B-from-Qwen3-8B_regen-speculators.eagle31-llamaarch-ckpt1
1B • Updated • 14
inference-optimization/Qwen3-8B-speculator.dflash.swa.non-qwen3-step189036
2B • Updated • 7
inference-optimization/Qwen3-8B-speculator.dflash.swa.causal-qwen235b-instruct-bs16-ckpt0
2B • Updated • 8
inference-optimization/Qwen3-8B-speculator.dflash.swa.non-qwen3-step126024
2B • Updated • 7
inference-optimization/Qwen3-8B-speculator.dflash.swa.non-qwen3-step84016
2B • Updated • 9
inference-optimization/Qwen3-8B-speculator.dflash.swa.non-qwen3-step63012
2B • Updated • 7
inference-optimization/Qwen3-8B-speculator.dflash.swa.non-qwen3-step42008
2B • Updated • 7
inference-optimization/Qwen3-8B-speculators.peagle-qwen3arch-ckpt4
2B • Updated • 8.21k • 1
inference-optimization/Qwen3-8B-speculator.dflash.swa.non-qwen3-step21004
2B • Updated • 8
inference-optimization/Laguna-XS.2-speculator.dflash-Qwen235B-500k-ckpt4
0.6B • Updated • 8