OLMo 2 7B

About the OLMo/Molmo (Ai2) family

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.

How this one is configured

This configuration ~7B parameters.

Who makes it

Allen Institute for AI — United States. Not listed as a provider in this directory.

More from OLMo/Molmo (Ai2)

• Molmo 7B-D
• Molmo2-8B
• OLMo 2 32B
• Olmo 3 32B Think
• Olmo 3 7B Instruct
• Olmo 3 7B Think
• Olmo 3.1 32B Instruct
• Olmo 3.1 32B Think