CodeComputer-use agentsMath and reasoningText

Flint

An open expert model (39.8B parameters, 2.5B active per token) for coding agents: it digs into someone else's repository, fixes bugs, writes functions and tests, and can reason and call tools over several steps. Trained from scratch, 262 thousand token context, text only. It weighs about 80 GB, and the authors run it on a single B300 or H200 card through SGLang. By the authors' own tests: Terminal-Bench 2.1 54.9%, SWE-bench Pro v2 89.7%, SWE-bench Verified 74.2%. Part of the comparisons come from other developers' own reports, and the test conditions differ between sources.

Developer
Recursive, not stated
First release
Oct 2026
Latest release
Oct 2026
Sizes
39.8B-A2.5B
License
Commercial use allowedApache 2.0
Russian
Not stated
Running
On your own serverNeeds a GPU
Industries
Software development, Security
Deploy on your server Hugging Face GitHub

What it does

  • an agent for fixing bugs and extending a repository in the terminal
  • writing tests and new functions from a description
  • a local developer assistant on your own server

Where it is used

software development and DevOpscompanies with their own graphics cardsinformation security (code review)

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
no versions
1 GPUOne GPU with 16–80 GB — mid-size versions
fits
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. Flint (BF16, 39.8B-A2.5B)

How to run it

On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.Hugging Face
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems.

Frequently asked questions

Can Flint be used in a commercial project?

Yes. License: Apache 2.0. It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does Flint need?

At minimum: One GPU with 16–80 GB — mid-size versions. Without a GPU the model is not practical. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does Flint support Russian?

The model card does not list languages, so Russian support cannot be promised — it has to be tested on your own examples.

Where can I download Flint and what does it cost?

The Flint weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.

How I deploy it for clients

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Similar models

CodeOrnithDeepReinforce · not disclosedCommercial use allowed

Models for agentic development: they build their own plan and scaffolding for a task and execute it in the terminal. Fine-tuned from Qwen 3.5 and Gemma 4; work with Claude Code, OpenHands and similar tools. In October Ornith-1.5-122B (MoE, MIT) came out: according to the authors it is stronger and faster than the previous ones, writes shorter and is meant for a single DGX-class card; compressed FP8, NVFP4, GGUF and MLX versions exist. The figures come from the authors.

DetailsCodeQwen CoderAlibaba (Qwen team) · ChinaCommercial use allowed

The broadest open coding family: from 0.5B for autocompletion to 480B for agents. Qwen3-Coder-Next (80B, 3B active) works as a developer agent on a single GPU.

DetailsCodeDevstralMistral AI (with All Hands AI) · FranceCommercial use with conditions

Mistral models for agentic development: they read the repository, edit files and run commands on their own. The 24B version fits on a single GPU.

Details

Source: huggingface.co/RecursiveSI/flint. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.