Code

Devstral

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.

Developer
Mistral AI (with All Hands AI), France
First release
May 2025
Latest release
Dec 2025
Sizes
24B – 123B
License
Commercial use with conditionsSmall 24B versions: Apache 2.0; Devstral 2 123B: modified MIT (not for companies with revenue above 20 million dollars per month)
Russian
Supported
Ready-made builds
GGUF, AWQ, GPTQ, MLX (Apple)
Running
Available in OllamaNeeds a GPU
Industries
Software development
Deploy on your server Hugging Face

What it does

  • A developer agent that fixes tickets from the tracker
  • Extending internal systems from a description
  • Automating routine code edits

Where it is used

IT departmentsProduct developmentImplementation and integrations

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
fits

Versions

  1. Devstral 2 123B и Devstral Small 2 24B
  2. Devstral Small 2507
  3. Devstral Small 2505

How to run it

With Ollama — the fastest wayInstall Ollama on your computer or server and find the model in its library by name. Good enough to try the model on your own tasks in one evening.Find it in the Ollama library
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. Quantization compresses a model so it takes less video memory and runs on more modest hardware. Answers change slightly, so quality is checked on your own examples.

Frequently asked questions

Can Devstral be used in a commercial project?

With conditions. License: Small 24B versions: Apache 2.0; Devstral 2 123B: modified MIT (not for companies with revenue above 20 million dollars per month). Restrictions vary — region, company revenue, attribution requirements. Have a lawyer check the terms before a commercial launch.

What hardware does Devstral 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 Devstral support Russian?

Yes, Russian is listed on the model card.

Where can I download Devstral and what does it cost?

The Devstral 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.

Comparisons

Similar models

CodeQwen 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.

DetailsCodeKAT-Coder / KAT-DevKwaipilot (Kuaishou) · ChinaCommercial use allowed

Kuaishou models for agentic development, trained to solve real tasks in repositories. KAT-Coder-V2.5-Dev (35B, 3B active) is the open version of their closed flagship.

DetailsCodeSERA (Ai2 Open Coding Agents)Ai2 (Allen Institute for AI) · USACommercial use allowed

Fully open developer agents from Ai2: weights, data and training recipe are all public. Designed so a company can cheaply fine-tune the agent on its own repository.

Details

Source: huggingface.co/mistralai/Devstral-2-123B-Instruct-2512. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.