Mini-K3-1H-llama-gqa-block4-v1
nkkbr/Mini-K3-1H-llama-gqa-block4-v1
Tracked by OpenModelStats since September 25, 2026View on Hugging Face ↗
- Downloads 30DRolling recent-window download count as reported by the source platform.
- 3,048
- Total downloadsCumulative all-time download counter reported by the source platform.
- 3,048
- Gained 7DIncrease in cumulative total downloads between OpenModelStats' own observations seven days apart.
- —
- Gained 30DIncrease in cumulative total downloads between OpenModelStats' own observations roughly thirty days apart.
- —
- LikesCommunity likes reported by the source platform.
- 0
- Rank · tracked modelsPosition among all eligible models tracked by OpenModelStats, ordered by recent downloads. #4145 among tracked Text Generation models.
- #15,826
- 34(up 34 places)this week
- Parameters
- 966M
- Last source update
- Sep 28, 2026
- It moved from #4138 to #4145 among tracked Text Generation models this week.
Downloads over time
Cumulative total downloads observed by OpenModelStatsLikes over time
Rank among tracked models
Lower is betterOverview
Mini-K3-1H-llama-gqa-block4-v1 is a text generation model published by nkkbr. OpenModelStats has tracked the model since Sep 25, 2026, most recently observing it Oct 4, 2026.
- Published
- Sep 25, 2026
- Last updated
- Sep 28, 2026
- Library
- pytorch
- License
- —
- Task
- Text Generation
- Parameters
- 966,352,640
- Spaces
- —
- Derivative models
- —
- Velocity 7D/day
- —
pytorchsafetensorsmini_k3kimi-k3pretrainingmixture-of-expertsllama-style-attentionarchitecture-ablationtext-generationregion:us
Publisher
nkkbrView publisher statistics →Similar models
| Model | DL 30D |
|---|---|
| Mini-K3-1H-llama-gqa-standard-v1nkkbr | 3,262 |
| Qwen3.8-1.0B-A0.6Binference-optimization | 4,487 |
| Nemotron-Flash-1Bnvidia | 2,786 |
| NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4-DSpark-MLXSawfwair | 424 |
| NVIDIA-Nemotron-3.5-Lightning-30B-A3B-DSpark-bf16mlx-community | 397 |
| SmolLM3-3B-trellis-3inst-4bpw-kernelxv0y5ncu | 3,735 |