Ai2: Olmo 3 7B Instruct
Model Type
Open Weight Model
7B parameters
Recommended Use Cases
Text Generation
Try Olmo 3 7B Instruct
The Instruct model from the OLMo 3 model family — a fully open 7B parameter instruction-tuned model from Ai2 (Allen Institute for AI). Unlike other open LLMs, OLMo provides complete access to training data, code, checkpoints, and logs.
Per its creators, Ai2:
OLMo 3 7B Instruct is a model for efficient inference that handles multi-turn chat, tool use, and more.
A smaller, lighter-weight model able to run on a wider range of hardware while delivering competitive performance.
Key Capabilities
- Math: 87.3% on MATH, 44.3% on AIME 2024
- Coding: 77.2% on HumanEvalPlus, 60.2% on MBPP+
- Reasoning: 71.2% on BigBenchHard, 32.9% on ZebraLogic
- Instruction Following: 85.6% on IFEval
- Tool Use: 79.3% on SimpleQA, 49.8% on BFCL