{"slug": "thinking-machines-shrinks-inkling-to-26b-parameters-and-puts-it-on-a-laptop", "title": "Thinking Machines shrinks Inkling to 26B parameters and puts it on a laptop", "summary": "Thinking Machines Lab released Inkling 2 Mini on November 20th, a 26.4B-parameter open-weights model built to run locally on Macs with 32GB of RAM while handling agentic coding and other tool-using work. The lab, led by co-founder and CEO Mira Murati, said Inkling 2 Mini loops its middle layers three times per token and scores 20.1 on the AA Index by the lab's count.", "body_md": "# Thinking Machines shrinks Inkling to 26B parameters and puts it on a laptop\n\n**Inkling 2 Mini loops its middle layers three times per token, scores 20.1 on the AA Index by the lab's count, and runs on Macs with 32GB of RAM.**\n\n        By [Ryan Merket](https://runtimewire.com/author/ryan-merket)\n        · Published \n\nThinking Machines Lab released Inkling 2 Mini on November 20th, a 26.4B-parameter open-weights model built to run locally while handling agentic coding and other tool-using work. The lab, led by co-founder and CEO Mira Murati, announced the model in a thread on X and detailed it in Introducing Inkling 2 Mini.…", "url": "https://wpnews.pro/news/thinking-machines-shrinks-inkling-to-26b-parameters-and-puts-it-on-a-laptop", "canonical_source": "https://runtimewire.com/article/thinking-machines-shrinks-inkling-to-26b-parameters-and-puts-it-on-a-laptop", "published_at": "2026-11-21 03:02:29+00:00", "updated_at": "2026-11-21 03:13:12.659579+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-agents", "ai-tools", "ai-research"], "entities": ["Thinking Machines Lab", "Inkling 2 Mini", "Mira Murati", "AA Index"], "also_reported_by": [], "takeaway": "Inkling 2 Mini is a 26.4B-parameter open-weights model that loops its middle layers three times per token and runs locally on Macs with 32GB of RAM, scoring 20.1 on the AA Index by the lab's count.", "recommendation": null, "alternates": {"html": "https://wpnews.pro/news/thinking-machines-shrinks-inkling-to-26b-parameters-and-puts-it-on-a-laptop", "markdown": "https://wpnews.pro/news/thinking-machines-shrinks-inkling-to-26b-parameters-and-puts-it-on-a-laptop.md", "text": "https://wpnews.pro/news/thinking-machines-shrinks-inkling-to-26b-parameters-and-puts-it-on-a-laptop.txt", "jsonld": "https://wpnews.pro/news/thinking-machines-shrinks-inkling-to-26b-parameters-and-puts-it-on-a-laptop.jsonld"}}