tools
OLMo
OLMo is Ai2’s fully open language model family with public weights, data, code, checkpoints, and evaluations.
In inglese
OLMo provides language models for research, development, and local deployment. Its model flow includes pretraining, mid-training, post-training, datasets, checkpoints, training code, and evaluation tools.
The current product page presents the Olmo 3 family in 7B and 32B Base, Think, and Instruct variants. Ai2 provides artifacts for download and documentation for running models locally; hosted usage pricing was not found.
Features
- Olmo 3 models in 7B and 32B Base, Think, and Instruct variants
- Public model weights, training data, checkpoints, code, and evaluations
- Supports programming, reading comprehension, mathematics, and extended-context tasks
- Think variants provide reasoning-focused checkpoints
- Instruct variants support chat, tool use, and multi-turn dialogue
- OlmoCore provides a framework for language-model training
- OLMES provides tools for reproducible model evaluation
- Open Instruct provides a post-training pipeline
Use cases
- Run language models locally on available hardware
- Fine-tune base checkpoints for specialized applications
- Study how training data and methods affect model behavior
- Build chat and tool-use systems with instruction-tuned checkpoints
- Reproduce or extend language-model training experiments
Pros
Cons
Latest updates
- v2.6.0 (v2.6.0)
Added a checkpoint retention limit and OutputDiscardCheckpoint activation recomputation.
- v2.5.0 (v2.5.0)
Added an exponential LR scheduler, Peri-LN transformer block, and support for loading and averaging multiple checkpoints.
- v2.4.0 (v2.4.0)
Added trainer step-range skipping, chat interaction for OlmoCore models, GAP monitoring, and official Olmo 3 pretraining scripts and data mix.
- v2.2.0 (v2.2.0)
- v2.1.0 (v2.1.0)
Added auxiliary-loss-free and sequence-level MoE load balancing, B200 compatibility, warmup fractions, and a 50B Dolmino 11/24 mix.
Capabilities
- Self-hosted — “Olmo 3 is a family of compact, dense models at 7 billion and 32 billion parameters that can run on everything from laptops to research clusters.” source
- API — “or use them via API courtesy of our inference partners.” source
- Runs models for you — “or use them via API courtesy of our inference partners.” source
Get it
Pricing
- Prices checked
- 2026-09-25