Olmo-3.1 32B Instruct

Olmo-3.1 32B Instruct is a powerful open-language model from the Olmo 3 family, specifically designed for conversational and reasoning tasks. It is pre-trained on the Dolma 3 dataset and post-trained on Dolci datasets, offering high-level performance across math, coding, and general reasoning benchmarks.

Olmo-3.1 32B Instruct is a powerful open-language model from the Olmo 3 family, specifically designed for conversational and reasoning tasks. It is pre-trained on the Dolma 3 dataset and post-trained on Dolci datasets, offering high-level performance across math, coding, and general reasoning benchmarks.

• 0132-billion parameter autoregressive transformer architecture
• 02Enhanced reasoning capabilities for complex math and coding tasks
• 03Permissive Apache 2.0 licensing for research and commercial use
• 04Seamless integration with Transformers, vLLM, and SGLang
• 05Trained on high-quality Dolma 3 and Dolci-Instruct-RL datasets