--- title: Recursive Flint is a mixture-of-experts model built for... description: Recursive released Flint, a mixture-of-experts model built for fast agentic coding on local hardware. It has 40 billion total parameters but activates only 2.5... canonical: https://daily.dev/posts/recursive-flint-is-a-mixture-of-experts-model-built-for-fast-agentic-coding-on-local-hardware-it-ha-3ubaoteqc twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Recursive Flint is a mixture-of-experts model built for fast agentic coding on local hardware. It has 40 billion total parameters but activates just 2.5 billion per token. It was built from scratch by a small team of people and agents in under four m | daily.dev og:description: Recursive released Flint, a mixture-of-experts model built for fast agentic coding on local hardware. It has 40 billion total parameters but activates only 2.5... og:url: https://daily.dev/posts/recursive-flint-is-a-mixture-of-experts-model-built-for-fast-agentic-coding-on-local-hardware-it-ha-3ubaoteqc og:image: https://api.daily.dev/og/posts/3UBAOtEQc.png og:image:alt: Recursive Flint is a mixture-of-experts model built for fast agentic coding on local hardware. It has 40 billion total parameters but activates just 2.5 billion per token. It was built from scratch by a small team of people and agents in under four m og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Recursive Flint is a mixture-of-experts model built for fast agentic coding on local hardware. It has 40 billion total parameters but activates just 2.5 billion per token. It was built from scratch by a small team of people and agents in under four m **[ml-research](https://daily.dev/sources/mlresearch)** · [@andrewma](https://daily.dev/andrewma) · 3 upvotes · 0 comments ## Summary Recursive released Flint, a mixture-of-experts model built for fast agentic coding on local hardware. It has 40 billion total parameters but activates only 2.5 billion per token, and the team built it from scratch in under four months. Flint leads MoE models under 50 billion total parameters on SWE-Bench Pro v2, Terminal-Bench 2.1, and SWE-Bench Verified, and generates more than 125 tokens per second on an M4 Pro MacBook Pro at short contexts. It supports context windows of up to 512k tokens, works with llama.cpp, Ollama, vLLM, and SGLang, and is available on Hugging Face under Apache 2.0. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [Needle 2 - The 14 MB Agentic LLM for Tiny Devices](https://daily.dev/posts/needle-2---the-14-mb-agentic-llm-for-tiny-devices-eu1fgqsim) · Hacker News · 4 upvotes · 0 comments --- Tags: [#data-science](https://daily.dev/tags/data-science), [#ai-coding](https://daily.dev/tags/ai-coding), [#local-ai](https://daily.dev/tags/local-ai), [#mixture-of-experts](https://daily.dev/tags/mixture-of-experts), [#huggingface](https://daily.dev/tags/huggingface) [View this post on daily.dev](https://daily.dev/posts/recursive-flint-is-a-mixture-of-experts-model-built-for-fast-agentic-coding-on-local-hardware-it-ha-3ubaoteqc) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"DiscussionForumPosting","mainEntityOfPage":"https://daily.dev/posts/recursive-flint-is-a-mixture-of-experts-model-built-for-fast-agentic-coding-on-local-hardware-it-ha-3ubaoteqc","headline":"Recursive Flint is a mixture-of-experts model built for fast agentic coding on local hardware. It has 40 billion total parameters but activates just 2.5 billion per token. It was built from scratch by a small team of people and agents in under four m","text":"Shared: Introducing Flint","url":"https://daily.dev/posts/recursive-flint-is-a-mixture-of-experts-model-built-for-fast-agentic-coding-on-local-hardware-it-ha-3ubaoteqc","datePublished":"2026-10-22T23:09:35.900Z","dateModified":"2026-10-23T00:30:40.603Z","author":{"@type":"Person","name":"Andrew M","url":"https://daily.dev/andrewma","image":"https://avatars.githubusercontent.com/u/102819214?v=4","description":"full time overthinker\n","interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"EndorseAction"},"userInteractionCount":2760}},"image":"https://media.daily.dev/image/upload/s--58gMhC4P--/f_auto/v1722860399/public/Placeholder%2012","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":2},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"sharedContent":{"@type":"WebPage","url":"https://api.daily.dev/r/swZBqbFeI"},"isPartOf":{"@type":"WebPage","url":"https://daily.dev/squads/mlresearch","name":"ml-research"}} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"ml-research","item":"https://daily.dev/squads/mlresearch"},{"@type":"ListItem","position":3,"name":"Recursive Flint is a mixture-of-experts model built for fast agentic coding on local hardware. It has 40 billion total parameters but activates just 2.5 billion per token. It was built from scratch by a small team of people and agents in under four m"}]} ```