---
title: "Recursive releases Flint, open-weight 40B coding model for laptops"
url: https://www.parallelquant.com/posts/recursive-releases-flint-open-weight-40b-coding-model-for-laptops-06bd6f
source_name: "MarkTechPost"
source_url: https://www.marktechpost.com/2026/10/21/recursive-flint-local-coding-model/
published: 2026-10-21T22:39:41.000Z
topics: ["open source", "llms", "products"]
publisher: "Parallel Quant"
---

# Recursive releases Flint, open-weight 40B coding model for laptops

*2026-10-21 · Source: [MarkTechPost](https://www.marktechpost.com/2026/10/21/recursive-flint-local-coding-model/)*

Recursive released Flint, an Apache 2.0 mixture-of-experts coding model with 40B total and 2.5B active parameters. It reports 74.2% on SWE-bench Verified and 125+ tokens per second on an M4 Pro MacBook Pro. TechCrunch reports it was built largely by Recursive's own AI research system.

**Why it matters:** A 2.5B-active model at this benchmark level makes capable local coding agents plausible on consumer hardware, cutting API dependence. If the 'largely AI-built' claim holds, it is also an early data point for AI-driven model development, a theme running through this month's agent and harness releases.

**Topics:** open source, llms, products

---
Read the original: https://www.marktechpost.com/2026/10/21/recursive-flint-local-coding-model/
Canonical: https://www.parallelquant.com/posts/recursive-releases-flint-open-weight-40b-coding-model-for-laptops-06bd6f
Published by Parallel Quant — https://www.parallelquant.com