https://www.anchorterminal.com/tools/olmo-3-7b-think Dated changes, score moves with their causes, what our workers noticed, and reviews for Olmo 3 7B Think. en Wed, 21 Oct 2026 21:59:57 +0000 https://www.anchorterminal.com/tools/olmo-3-7b-think#rev_3963 https://www.anchorterminal.com/tools/olmo-3-7b-think#rev_3963 Wed, 21 Oct 2026 00:00:00 +0000 review Ai2 last changed this repository on 25 June 2026, a parameter-count fix on the card, 118 days before this check. The training data is published in full with sources and sizes. None of the 3 discussions has an Ai2 reply, including a vLLM report open since 24 November 2025, and the template's default prompt gives a November 2024 cut-off where the card says December 2024. A stray editor swap file sits in the repository. GitHub replies weren't counted. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/olmo-3-7b-think#rev_3964 https://www.anchorterminal.com/tools/olmo-3-7b-think#rev_3964 Wed, 21 Oct 2026 00:00:00 +0000 review Ollama's and LM Studio's Q4_K_M builds are 4.5 GB, so an 8 GB machine holds it, and Ai2's BF16 files are 14.6 GB. Ai2 publishes no quantised build of its own. The metadata names Apache 2.0, but there is no LICENSE file, and the card ties use to Ai2's Responsible Use Guidelines, which list disallowed uses and which Ai2 may update at any time. No inference provider or Ai2 API serves it, so hardware is the only route. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/olmo-3-7b-think#rev_3965 https://www.anchorterminal.com/tools/olmo-3-7b-think#rev_3965 Wed, 21 Oct 2026 00:00:00 +0000 review Olmo 3 7B Think ships chat_template.jinja, and only that template and vLLM's olmo3 parser describe tool calls. Ai2's report says tool calling was trained into the Instruct model, while Think reads the function tags as plain text. Every reply opens a think block with no switch or budget, JSON output isn't documented, and context is 65,536 tokens. Of 9 independent results from Artificial Analysis, tau2-bench Telecom and AA-LCR both record 0.0. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/olmo-3-7b-think#rev_3966 https://www.anchorterminal.com/tools/olmo-3-7b-think#rev_3966 Wed, 21 Oct 2026 00:00:00 +0000 review Olmo 3 7B Think loads from three safetensors shards with chat_template.jinja, so no repository code runs, and every shard has a SHA-256 in the allenai organisation. Ai2 publishes safety results on HarmBench, XSTest, WildJailbreak and others, and OLMES lets anyone rerun them. Agent guidance stops at general cautions, with nothing on prompt injection. The Responsible Use Guidelines add disallowed uses and let Ai2 update them or end access at its discretion. Ai2's security.txt expired on 31 July 2026. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/olmo-3-7b-think https://www.anchorterminal.com/tools/olmo-3-7b-think#run-2026-10-01 Thu, 01 Oct 2026 00:00:00 +0000 listing Olmo 3 7B Think is Ai2's fully open 7B reasoning model for maths, code and step-by-step answers, with training data, code and checkpoints published, a 65,536-token context and thinking always on, released in November 2025 under Apache 2.0.