Latest research
October 7, 2026
Now in Nature: Retrofitting language models to operate over bytes
The technique behind Bolmo, Ai2’s fully open byte-level language models, is now published in Nature, with new checkpoints showing the approach generalizes beyond Olmo to other model families.October 1, 2026
Introducing Olmo-core 3: Open, scalable training infrastructure for large MoEs
Olmo-core 3 introduces a redesigned, fully open training stack for efficiently scaling mixture-of-experts models into the trillion-parameter range.June 25, 2026
Which tokens does a hybrid model predict better?
New token-level analyses of Olmo 3 and Olmo Hybrid show that hybrid models predict meaning-bearing, context-dependent tokens better than transformers, while transformers retain an edge on verbatim copying.June 12, 2026
olmo-eval: An evaluation workbench for the model development loop
olmo-eval is an open evaluation workbench that helps model developers add, run, and analyze benchmarks across changing LLM checkpoints, extending OLMES from final-score reproducibility into the day-to-day model development loop.April 23, 2026
OlmPool: How small architectural choices compound to undermine long context extension
OlmPool is a controlled suite of 26 models showing how small architecture choices can compound to make long-context extension much harder, even when training data and extension recipes are held constant.March 5, 2026
Introducing Olmo Hybrid: Combining transformers and linear RNNs for superior scaling
Olmo Hybrid is a fully open 7B language model that combines transformer attention with linear RNN layers to achieve greater expressivity and significantly improved data and compute efficiency compared to pure transformer models.February 13, 2026
Olmix: A framework for data mixing throughout LM development
Olmix is a framework for language model data mixing that provides empirically grounded defaults and efficient reuse techniques.December 15, 2025
Introducing Bolmo: Byteifying the next generation of language models
Bolmo is new a byte-level family built by adapting Olmo 3 into a fast, flexible byte-based model with a short extra training run.November 20, 2025
Olmo 3: Charting a path through the model flow to lead open-source AI
Our new flagship Olmo 3 model family empowers the open source community with not only state-of-the-art open models, but the entire model flow and full traceability back to training data.1-9Next