Devstral Small 2505 FP8 Dynamic

🚀 Devstral-Small-2505

Devstral is an agentic LLM tailored for software engineering tasks. It's the result of a collaboration between Mistral AI and All Hands AI 🙌. This model shines at leveraging tools to explore codebases, edit multiple files, and power software engineering agents. It achieves remarkable performance on SWE-bench, positioning it as the #1 open-source model on this benchmark.

It is fine-tuned from Mistral-Small-3.1, boasting a long context window of up to 128k tokens. As a coding agent, Devstral is text-only, and the vision encoder was removed before fine-tuning from Mistral-Small-3.1.

For enterprises in need of specialized capabilities (such as increased context or domain-specific knowledge), we'll release commercial models beyond what Mistral AI contributes to the community.

Learn more about Devstral in our blog post.

🚀 Quick Start

Quantized to FP8-Dynamic with LLMCompressor

vllm serve nm-testing/Devstral-Small-2505-FP8-dynamic --tokenizer_mode mistral

✨ Features

• Agentic coding: Devstral is engineered to excel at agentic coding tasks, making it an ideal choice for software engineering agents.
• Lightweight: With a compact size of just 24 billion parameters, Devstral is light enough to run on a single RTX 4090 or a Mac with 32GB RAM, suitable for local deployment and on-device use.
• Apache 2.0 License: An open license that permits usage and modification for both commercial and non-commercial purposes.
• Context Window: It has a 128k context window.
• Tokenizer: Utilizes a Tekken tokenizer with a 131k vocabulary size.

📚 Documentation

Benchmark Results

SWE-Bench

Devstral achieves a score of 46.8% on SWE-Bench Verified, outperforming the prior open-source SoTA by 6%.

When evaluated under the same test scaffold (OpenHands, provided by All Hands AI 🙌), Devstral outperforms far larger models such as Deepseek-V3-0324 and Qwen3 232B-A22B.

Usage

We recommend using Devstral with the OpenHands scaffold. You can use it either through our API or by running it locally.

API

Follow these instructions to create a Mistral account and get an API key.

Then run these commands to start the OpenHands docker container.

export MISTRAL_API_KEY=<MY_KEY>

docker pull docker.all-hands.dev/all-hands-ai/runtime:0.39-nikolaik

mkdir -p ~/.openhands-state && echo '{"language":"en","agent":"CodeActAgent","max_iterations":null,"security_analyzer":null,"confirmation_mode":false,"llm_model":"mistral/devstral-small-2505","llm_api_key":"'$MISTRAL_API_KEY'","remote_runtime_resource_factor":null,"github_token":null,"enable_default_condenser":true}' > ~/.openhands-state/settings.json

docker run -it --rm --pull=always \
    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.39-nikolaik \
    -e LOG_ALL_EVENTS=true \
    -v /var/run/docker.sock:/var/run/docker.sock \
    -v ~/.openhands-state:/.openhands-state \
    -p 3000:3000 \
    --add-host host.docker.internal:host-gateway \
    --name openhands-app \
    docker.all-hands.dev/all-hands-ai/openhands:0.39

Local inference

The model can also be deployed with the following libraries:

• vllm (recommended): See here
• mistral-inference: See here
• transformers: See here
• LMStudio: See here
• ollama: See here

OpenHands (recommended)

Launch a server to deploy Devstral-Small-2505

Make sure you've launched an OpenAI-compatible server such as vLLM or Ollama as described above. Then, you can use OpenHands to interact with Devstral-Small-2505.

In the case of the tutorial, we spun up a vLLM server by running the command:

vllm serve mistralai/Devstral-Small-2505 --tokenizer_mode mistral --config_format mistral --load_format mistral --tool-call-parser mistral --enable-auto-tool-choice --tensor-parallel-size 2

The server address should be in the following format: http://<your-server-url>:8000/v1

Launch OpenHands

You can follow the installation of OpenHands here.

The easiest way to launch OpenHands is to use the Docker image:

docker pull docker.all-hands.dev/all-hands-ai/runtime:0.38-nikolaik

docker run -it --rm --pull=always \
    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.38-nikolaik \
    -e LOG_ALL_EVENTS=true \
    -v /var/run/docker.sock:/var/run/docker.sock \
    -v ~/.openhands-state:/.openhands-state \
    -p 3000:3000 \
    --add-host host.docker.internal:host-gateway \
    --name openhands-app \
    docker.all-hands.dev/all-hands-ai/openhands:0.38

Then, you can access the OpenHands UI at http://localhost:3000.

Connect to the server

When accessing the OpenHands UI, you'll be prompted to connect to a server. You can use the advanced mode to connect to the server you launched earlier.

Fill in the following fields:

• Custom Model: openai/mistralai/Devstral-Small-2505
• Base URL: http://<your-server-url>:8000/v1
• API Key: token (or any other token you used to launch the server if applicable)

Use OpenHands powered by Devstral

Now you're ready to use Devstral Small inside OpenHands by starting a new conversation. Let's build a To-Do list app.

Build a To-Do list app with the following requirements:
- Built using FastAPI and React.
- Make it a one page app that:
   - Allows to add a task.
   - Allows to delete a task.
   - Allows to mark a task as done.
   - Displays the list of tasks.
- Store the tasks in a SQLite database.

vLLM (recommended)

We recommend using this model with the vLLM library to implement production-ready inference pipelines.

Installation Make sure you install vLLM >= 0.8.5:

pip install vllm --upgrade

Doing so should automatically install mistral_common >= 1.5.5.

To check:

python -c "import mistral_common; print(mistral_common.__version__)"

You can also make use of a ready-to-go docker image or on the docker hub.

Server

We recommend using Devstral in a server/client setting.

1. Spin up a server:

vllm serve mistralai/Devstral-Small-2505 --tokenizer_mode mistral --config_format mistral --load_format mistral --tool-call-parser mistral --enable-auto-tool-choice --tensor-parallel-size 2

2. To ping the client, you can use a simple Python snippet.

import requests
import json
from huggingface_hub import hf_hub_download


url = "http://<your-server-url>:8000/v1/chat/completions"
headers = {"Content-Type": "application/json", "Authorization": "Bearer token"}

model = "mistralai/Devstral-Small-2505"

def load_system_prompt(repo_id: str, filename: str) -> str:
    file_path = hf_hub_download(repo_id=repo_id, filename=filename)
    with open(file_path, "r") as file:
        system_prompt = file.read()
    return system_prompt

SYSTEM_PROMPT = load_system_prompt(model, "SYSTEM_PROMPT.txt")

messages = [
    {"role": "system", "content": SYSTEM_PROMPT},
    {
        "role": "user",
        "content": [
            {
                "type": "text",
                "text": "<your-command>",
            },
        ],
    },
]

data = {"model": model, "messages": messages, "temperature": 0.15}

response = requests.post(url, headers=headers, data=json.dumps(data))
print(response.json()["choices"][0]["message"]["content"])

Mistral-inference

We recommend using mistral-inference to quickly try out / "vibe-check" Devstral.

Install

Make sure to have mistral_inference >= 1.6.0 installed.

pip install mistral_inference --upgrade

Download

from huggingface_hub import snapshot_download
from pathlib import Path

mistral_models_path = Path.home().joinpath('mistral_models', 'Devstral')
mistral_models_path.mkdir(parents=True, exist_ok=True)

snapshot_download(repo_id="mistralai/Devstral-Small-2505", allow_patterns=["params.json", "consolidated.safetensors", "tekken.json"], local_dir=mistral_models_path)

Python

You can run the model using the following command:

mistral-chat $HOME/mistral_models/Devstral --instruct --max_tokens 300

You can then prompt it with anything you'd like.

Transformers

To make the best use of our model with transformers, make sure to have installed mistral-common >= 1.5.5 to use our tokenizer.

pip install mistral-common --upgrade

Then load our tokenizer along with the model and generate:

import torch

from mistral_common.protocol.instruct.messages import (
    SystemMessage, UserMessage
)
from mistral_common.protocol.instruct.request import ChatCompletionRequest
from mistral_common.tokens.tokenizers.mistral import MistralTokenizer
from mistral_common.tokens.tokenizers.tekken import SpecialTokenPolicy
from huggingface_hub import hf_hub_download
from transformers import AutoModelForCausalLM

def load_system_prompt(repo_id: str, filename: str) -> str:
    file_path = hf_hub_download(repo_id=repo_id, filename=filename)
    with open(file_path, "r") as file:
        system_prompt = file.read()
    return system_prompt

model_id = "mistralai/Devstral-Small-2505"
tekken_file = hf_hub_download(repo_id=model_id, filename="tekken.json")
SYSTEM_PROMPT = load_system_prompt(model_id, "SYSTEM_PROMPT.txt")

tokenizer = MistralTokenizer.from_file(tekken_file)

model = AutoModelForCausalLM.from_pretrained(model_id)

tokenized = tokenizer.encode_chat_completion(
    ChatCompletionRequest(
        messages=[
            SystemMessage(content=SYSTEM_PROMPT),
            UserMessage(content="<your-command>"),
        ],
    )
)

output = model.generate(
    input_ids=torch.tensor([tokenized.tokens]),
    max_new_tokens=1000,
)[0]

decoded_output = tokenizer.decode(output[len(tokenized.tokens):])
print(decoded_output)

LMStudio

Download the weights from huggingface:

pip install -U "huggingface_hub[cli]"
huggingface-cli download \
"mistralai/Devstral-Small-2505_gguf" \
--include "devstralQ4_K_M.gguf" \
--local-dir "mistralai/Devstral-Small-2505_gguf/"

You can serve the model locally with LMStudio.

• Download LM Studio and install it
• Install lms cli ~/.lmstudio/bin/lms bootstrap
• In a bash terminal, run lms import devstralQ4_K_M.gguf in the directory where you've downloaded the model checkpoint (e.g., mistralai/Devstral-Small-2505_gguf)
• Open the LMStudio application, click the terminal icon to enter the developer tab. Click "Select a model to load" and select Devstral Q4 K M. Toggle the status button to start the model, and in settings, toggle "Serve on Local Network" to be on.
• On the right tab, you'll see an API identifier which should be devstralq4_k_m and an api address under API Usage. Keep note of this address, as we'll use it in the next step.

Launch Openhands You can now interact with the model served from LM Studio with openhands. Start the openhands server with the docker

docker pull docker.all-hands.dev/all-hands-ai/runtime:0.38-nikolaik
docker run -it --rm --pull=always \
    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.38-nikolaik \
    -e LOG_ALL_EVENTS=true \
    -v /var/run/docker.sock:/var/run/docker.sock \
    -v ~/.openhands-state:/.openhands-state \
    -p 3000:3000 \
    --add-host host.docker.internal:host-gateway \
    --name openhands-app \
    docker.all-hands.dev/all-hands-ai/openhands:0.38

Click “see advanced setting” on the second line. In the new tab, toggle advanced to on. Set the custom model to be mistral/devstralq4_k_m and Base URL to the api address we got from the last step in LM Studio. Set API Key to dummy. Click save changes.

Ollama

You can run Devstral using the Ollama CLI.

ollama run devstral

📄 License

This project is licensed under the Apache 2.0 license.