OLMo/Molmo (Ai2)
9 models · Allen Institute for AI
The Allen Institute's fully open models — OLMo/Olmo 3 (7B–32B, Think variants) release weights, data, code AND training logs; Molmo adds open vision-language; Tulu is its open post-training recipe applied at 405B scale.
Models in this family
- Molmo 7B-DAllen Institute for AIOpen7B parametersResearch
- Molmo2-8BAllen Institute for AIOpen8B parametersResearch
- OLMo 2 32BAllen Institute for AIOpen32B parametersResearch
- OLMo 2 7BAllen Institute for AIOpen7B parametersResearch
- Olmo 3 32B ThinkAllen Institute for AIOpen32B parametersResearch
- Olmo 3 7B InstructAllen Institute for AIOpen7B parametersResearch
- Olmo 3 7B ThinkAllen Institute for AIOpen7B parametersResearch
- Olmo 3.1 32B InstructAllen Institute for AIOpen32B parametersResearch
- Olmo 3.1 32B ThinkAllen Institute for AIOpen32B parametersResearch