Particle.news
Download on the App Store

Ai2 Releases Olmo 3, Opening the Entire LLM "Model Flow" to the Public

The nonprofit makes the full development lifecycle inspectable by releasing models, datasets, code, checkpoints and tools.

Overview

  • Ai2 published Olmo 3 under the Apache 2.0 license with weights, training checkpoints and evaluation assets available on Hugging Face.
  • The family includes Base (7B, 32B), Think (7B, 32B) and Instruct (7B), with a reported RLZero variant adapted for reinforcement learning.
  • The release exposes end-to-end development details such as data recipes, dependencies and intermediate checkpoints, alongside tools like OlmoTrace for inspecting reasoning traces and linking outputs to training data.
  • Curated data drops feature the Dolma 3 pretraining corpus and Dolci post-training suites for SFT, DPO and RLVR, with deduplication and OCR applied to scientific papers.
  • Ai2 reports competitive benchmark results for the reasoning-focused Think models and training efficiency gains including 8x SFT throughput and 4x more efficient RL, with performance and efficiency claims awaiting independent validation.