h2o-lightning-4b-mlx-q8
netprojects/h2o-lightning-4b-mlx-q8
Tracked by OpenModelStats since October 12, 2026View on Hugging Face ↗
- Downloads 30DRolling recent-window download count as reported by the source platform.
- 466
- Total downloadsCumulative all-time download counter reported by the source platform.
- 466
- 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.
- 3
- Rank · tracked modelsPosition among all eligible models tracked by OpenModelStats, ordered by recent downloads. #4645 among tracked Image Text to Text models.
- #48,737
- 385(down 385 places)this week
- Parameters
- 4.5B
- Last source update
- Oct 25, 2026
- It moved from #4598 to #4645 among tracked Image Text to Text models this week.
Downloads over time
Rolling recent-window downloads as reportedLikes over time
Rank among tracked models
Lower is betterOverview
h2o-lightning-4b-mlx-q8 is a image text to text model published by netprojects. OpenModelStats has tracked the model since Oct 12, 2026, most recently observing it Oct 25, 2026.
- Published
- Oct 12, 2026
- Last updated
- Oct 25, 2026
- Library
- mlx
- License
- apache-2.0
- Task
- Image Text to Text
- Parameters
- 4,539,265,536
- Spaces
- —
- Derivative models
- —
- Velocity 7D/day
- —
mlxsafetensorsqwen3_5decision-modeldecision-makingcalibrationjevbenchapple-siliconimage-text-to-textconversationalbase_model:h2oai/h2o-lightning-4bbase_model:quantized:h2oai/h2o-lightning-4b
Publisher
netprojectsView publisher statistics →Derived from h2oai/h2o-lightning-4b (reported by the source; parent not yet tracked).
Similar models
| Model | DL 30D |
|---|---|
| LightOnOCR-3-4Blightonai | 14.5K |
| Huihui-Qwen3.5-4B-abliteratedhuihui-ai | 11.9K |
| Qwen3.5-4B-MLX-4bitlmstudio-community | 11.1K |
| DeskForge-Qwen3.5-4Bdocling-project | 9,288 |
| Qwen-Drive-1.0-4BQwen | 7,167 |
| Qwen3.5-4B-MLX-8bitlmstudio-community | 5,974 |