by Allen AI
Molmo2-8B is an open vision-language model developed by the Allen Institute for AI (Ai2) as part of the Molmo2 family, supporting image, video, and multi-image understanding and grounding. It is based on Qwen3-8B and uses SigLIP 2 as its vision backbone, outperforming other open-weight, open-data models on short videos, counting, and captioning, while remaining competitive on long-video tasks.
| Signal | Strength | Weight | Impact |
|---|---|---|---|
| Recency2026-03-03T20:26:22.544Z | 100 | 15% | +15.0 |
| Context Window2026-03-03T20:26:22.544Z | 73 | 15% | +10.9 |
| Output Capacity2026-03-03T20:26:22.544Z | 76 | 10% | +7.6 |
| Capabilities2026-03-03T20:26:22.544Z | 29 | 25% | +7.1 |
| Versatility2026-03-03T20:26:22.544Z | 67 | 10% | +6.7 |
| Pricing Tier2026-03-03T20:26:22.544Z | 0 | 25% | +0.1 |
Cost Estimator
You save $38.79/month vs category average