inference-optimization AI Models
Tracked by OpenModelStats since Aug 23, 2026 · View on Hugging Face ↗
- Tracked modelsRepositories from this publisher currently tracked by OpenModelStats.
- 18
- Downloads 30DSum of each tracked model's rolling recent-downloads counter. A sum of repository counters is not a count of unique users.
- 181K
- Total downloadsSum of cumulative all-time download counters across tracked repositories.
- 377.9K
- Total likes
- 94
- Gained 7DCombined seven-day cumulative-download gains measured by OpenModelStats.
- —
Most downloaded
- 1Kimi-K3-0.40BJul 28, 202686K
- 2DeepSeek-V3-debug-empty-FP8_DYNAMICJan 23, 202621.4K
- 3Qwen3-8B-from-Qwen3-8B_regen-speculators.eagle3-qwen3arch-ckpt1Jun 10, 202616.9K
- 4Qwen3-8B-speculators.peagle-qwen3arch-ckpt4Jun 16, 202616.7K
- 5Llama-3.2-0.5B-InstructJun 3, 202616.6K
- 6Qwen3-1.6B-A0.9BMay 24, 20268,563
- 7GLM-5.2-0.8B-A0.8BJul 2, 20264,948
- 8DSV4-tiny-emptyMay 18, 20263,127
- 9Qwen3.8-1.0B-A0.6BAug 12, 20263,007
- 10DeepSeek-V3-debug-emptyJan 23, 20262,399
Recently updated
- 1DeepSeek-V4-Flash-NVFP4-REAP-50Aug 23, 202610
- 2DeepSeek-V4-Flash-NVFP4-REAP-25Aug 23, 20269
- 3Qwen3-8B-speculator.dspark.swa.gammatv.2048anc.muon.combdatav4-q235b-instr-v2-ckpt9Aug 23, 20260
- 4Qwen3-8B-speculator.dspark.swa.gammatv.2048anc.muon.combdatav4-q235b-instr-v2-ckpt8Aug 22, 20268
- 5gemma-4-26B-A4B-it-NVFP4-REAP-50Aug 22, 20269
- 6gemma-4-26B-A4B-it-NVFP4-REAP-25Aug 22, 20268
- 7Qwen3-8B-speculator.dspark.swa.gammatv.2048anc.muon.combdatav4-q235b-instr-v2-ckpt7Aug 22, 202612
- 8Qwen3.8-1.0B-A0.6BAug 12, 20263,007
- 9Kimi-K3-0.40B-MXFP4Jul 28, 20261,320
- 10Kimi-K3-0.40BJul 28, 202686K
All models
| Model | DL 30D | 7D |
|---|---|---|
| Kimi-K3-0.40Binference-optimization/kimi-k3-0.40b | 86K | — |
| DeepSeek-V3-debug-empty-FP8_DYNAMICinference-optimization/deepseek-v3-debug-empty-fp8_dynamic | 21.4K | — |
| Qwen3-8B-from-Qwen3-8B_regen-speculators.eagle3-qwen3arch-ckpt1inference-optimization/qwen3-8b-from-qwen3-8b_regen-speculators.eagle3-qwen3arch-ckpt1 | 16.9K | — |
| Qwen3-8B-speculators.peagle-qwen3arch-ckpt4inference-optimization/qwen3-8b-speculators.peagle-qwen3arch-ckpt4 | 16.7K | — |
| Llama-3.2-0.5B-Instructinference-optimization/llama-3.2-0.5b-instruct | 16.6K | — |
| Qwen3-1.6B-A0.9Binference-optimization/qwen3-1.6b-a0.9b | 8,563 | — |
| GLM-5.2-0.8B-A0.8Binference-optimization/glm-5.2-0.8b-a0.8b | 4,948 | — |
| DSV4-tiny-emptyinference-optimization/dsv4-tiny-empty | 3,127 | — |
| Qwen3.8-1.0B-A0.6Binference-optimization/qwen3.8-1.0b-a0.6b | 3,007 | — |
| DeepSeek-V3-debug-emptyinference-optimization/deepseek-v3-debug-empty | 2,399 | — |
| Kimi-K3-0.40B-MXFP4inference-optimization/kimi-k3-0.40b-mxfp4 | 1,320 | — |
| Qwen3-8B-speculator.dspark.swa.gammatv.2048anc.muon.combdatav4-q235b-instr-v2-ckpt7inference-optimization/qwen3-8b-speculator.dspark.swa.gammatv.2048anc.muon.combdatav4-q235b-instr-v2-ckpt7 | 12 | — |
| DeepSeek-V4-Flash-NVFP4-REAP-50inference-optimization/deepseek-v4-flash-nvfp4-reap-50 | 10 | — |
| DeepSeek-V4-Flash-NVFP4-REAP-25inference-optimization/deepseek-v4-flash-nvfp4-reap-25 | 9 | — |
| gemma-4-26B-A4B-it-NVFP4-REAP-50inference-optimization/gemma-4-26b-a4b-it-nvfp4-reap-50 | 9 | — |
| gemma-4-26B-A4B-it-NVFP4-REAP-25inference-optimization/gemma-4-26b-a4b-it-nvfp4-reap-25 | 8 | — |
| Qwen3-8B-speculator.dspark.swa.gammatv.2048anc.muon.combdatav4-q235b-instr-v2-ckpt8inference-optimization/qwen3-8b-speculator.dspark.swa.gammatv.2048anc.muon.combdatav4-q235b-instr-v2-ckpt8 | 8 | — |
| Qwen3-8B-speculator.dspark.swa.gammatv.2048anc.muon.combdatav4-q235b-instr-v2-ckpt9inference-optimization/qwen3-8b-speculator.dspark.swa.gammatv.2048anc.muon.combdatav4-q235b-instr-v2-ckpt9 | 0 | — |