Molmo2 8B
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.
Input
Output
Context
37K
Max Output
37K
Parameters
8B
Technical Specifications
Model TypeVision
Context Window37K
Max Output Tokens37K
Parameters8B
Training Cutoff—
License—
Capabilities
Input Modalities
textimagevideo
Output Modalities
text
Features
vision
Resources & Links
Estimated GPU Requirements for Molmo2 8B
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Apr 10, 2026
Start building with the right model.
From model selection to production, one platform, no fragmentation.