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

> The Apache 2.0 model activates 2.5B parameters per token and, the company says, leads open models under 50B on agentic coding benchmarks.

URL: https://claudegpt.si/news/recursive-flint-open-coding-model  
Published: 2026-10-25T06:49:02.216Z  
Author: ClaudeGPT Si Newsroom  
Section: AI Models  
Topics: Recursive, Flint, Open-weight models, Language models, Hugging Face  
Publisher: ClaudeGPT Si

## Key takeaways

- Recursive released Flint on October 23, with Apache 2.0 weights on Hugging Face.
- It has about 40B parameters, 2.5B active per token, and a context window of up to 512,000 tokens.
- Recursive reports 74.2% on SWE-bench Verified and 54.9% on Terminal-Bench 2.1, with no independent tests yet.

Recursive, a startup that says it is building self-improving AI, released [Flint](https://www.recursive.com/updates/introducing-recursive-flint) on October 23. Flint is an open-weight coding model small enough to run on a laptop: it has about 40 billion parameters but uses only 2.5 billion of them for each token.

That makes it a mixture-of-experts model, which means it runs only part of its network for each word it produces. The weights are on [Hugging Face](https://huggingface.co/RecursiveSI/flint) under the Apache 2.0 license, and the model was among the fastest-rising new releases on the site's trending list this week.

## What Recursive says Flint can do

Recursive built Flint for coding agents: investigating a codebase, fixing bugs, adding features and writing tests. The model card lists these scores from the company's own release evaluations:

- 54.9% on Terminal-Bench 2.1
- 89.7% on SWE-bench Pro v2
- 74.2% on SWE-bench Verified

Recursive says this makes Flint the strongest mixture-of-experts model under 50 billion parameters on agentic coding benchmarks. It also says Flint rivals dense models of 25 to 40 billion parameters while running more than five times faster. We have no independent test of either claim, and the post does not list the models it compared against.

## Fast enough to run locally

The context window goes up to 512,000 tokens, with 256,000 recommended for best results. Recursive reports more than 125 tokens per second on an M4 Pro MacBook Pro and more than 150 tokens per second on a 64GB Nvidia RTX Spark at short contexts. It says a 4-bit version loses 0.7 points or less against the full-precision model on its benchmarks.

Flint works with llama.cpp, Ollama, vLLM and SGLang, among other tools. Running it locally means no API fees. The model card says hosted API terms are separate, and Recursive has not published hosted pricing.

## The self-improvement claim

Recursive says its internal system, which it calls the Eureka Machine, helped build nearly every part of Flint's training stack. The system proposes ideas, implements them and tests them. According to the post, it found a 4-bit quantization of the output layer, paired with a distillation stage, that nearly halved the training steps compared with the company's baseline. It also produced inference kernels, the low-level code that runs the model on a chip.

The post gives no numbers beyond that, and the model card itself says only that Flint was trained from scratch through pretraining, supervised fine-tuning and reinforcement learning. Treat the "self-improving" label as the company's description of its tooling, not as a measured result.

## What we don't know yet

No paper is linked, and no one outside Recursive has published benchmark results. The company has not said how large its training run was or what data it used. Whether Flint holds up on real codebases, as opposed to benchmarks, is something developers will find out over the next few weeks. Recursive's code for running the model locally is on [GitHub](https://github.com/recursive-oss/rec).

## Sources

- [Introducing Recursive Flint](https://www.recursive.com/updates/introducing-recursive-flint), Recursive
- [RecursiveSI/flint model card](https://huggingface.co/RecursiveSI/flint), Hugging Face