Gemma4-26B-MoE-Q3T
mavis-ai/Gemma4-26B-MoE-Q3T
Tracked by OpenModelStats since October 4, 2026View on Hugging Face ↗
- Downloads 30DRolling recent-window download count as reported by the source platform.
- 14
- Total downloadsCumulative all-time download counter reported by the source platform.
- 14
- 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.
- —
- –this week
- Parameters
- 7.7B
- Last source update
- Oct 4, 2026
Downloads over time
Rolling recent-window downloads as reportedLikes over time
Rank among tracked models
Lower is betterNot enough tracked history yet for a chart.
OpenModelStats began tracking this model on 2026-10-04. Charts appear as daily observations accumulate.
Overview
Gemma4-26B-MoE-Q3T is a image text to text model published by mavis-ai. OpenModelStats has tracked the model since Oct 4, 2026, most recently observing it Oct 5, 2026.
- Published
- Oct 4, 2026
- Last updated
- Oct 4, 2026
- Library
- trellis
- License
- apache-2.0
- Task
- Image Text to Text
- Parameters
- 7,680,644,686
- Spaces
- —
- Derivative models
- —
- Velocity 7D/day
- —
trellissafetensorsgemma4moequantizedq3tapple-siliconspeculative-decodingmtpdflashimage-text-to-textconversational
Publisher
mavis-aiView publisher statistics →Derived from google/gemma-4-26B-A4B-it (reported by the source; parent not yet tracked).
Similar models
| Model | DL 30D |
|---|---|
| A.X-4.0-VL-Lightskt | 562 |
| gemma-4-26b-a4b-it-MLX-8bitunsloth | 975 |
| Molmo-7B-O-0924allenai | 3,531 |
| patram-7b-instructbharatgenai | 2,766 |
| NVIDIA-Nemotron-Nano-12B-v2-VL-NVFP4-QADnvidia | 169.2K |
| Gemma-4-12B-NVFP4AxionML | 915 |