π Model Description
base_model:
- mistralai/Devstral-2-123B-Instruct-2512
- mistral-common
- unsloth
- mistral
Read our How to Run Devstral 2 Guide!
Devstral 2 123B Instruct 2512
Devstral is an agentic LLM for software engineering tasks. Devstral 2 excels at using tools to explore codebases, editing multiple files and power software engineering agents. The model achieves remarkable performance on SWE-bench.This model is an Instruct model in FP8, fine-tuned to follow instructions, making it ideal for chat, agentic and instruction based tasks for SWE use cases.
For enterprises requiring specialized capabilities (increased context, domain-specific knowledge, etc.), we invite companies to reach out to us.
Key Features
The Devstral 2 Instruct model offers the following capabilities:- Agentic Coding: Devstral is designed to excel at agentic coding tasks, making it a great choice for software engineering agents.
- Improved Performance: Devstral 2 is a step-up compared to its predecessors.
- Better Generalization: Generalises better to diverse prompts and coding environments.
- Context Window: A 256k context window.
Use Cases
AI Code Assistants, Agentic Coding, and Software Engineering Tasks. Leveraging advanced AI capabilities for complex tool integration and deep codebase understanding in coding environments.
Benchmark Results
| Model/Benchmark | Size (B Parameters) | SWE Bench Verified | SWE Bench Multilingual | Terminal Bench 2 |
|---|---|---|---|---|
| Devstral 2 | 123 | 72.2% | 61.3% | 32.6% |
| Devstral Small 2 | 24 | 68.0% | 55.7% | 22.5% |
| GLM 4.6 | 455 | 68.0% | -- | 24.6% |
| Qwen 3 Coder Plus | 480 | 69.6% | 54.7% | 25.4% |
| MiniMax M2 | 230 | 69.4% | 56.5% | 30.0% |
| Kimi K2 Thinking | 1000 | 71.3% | 61.1% | 35.7% |
| DeepSeek v3.2 | 671 | 73.1% | 70.2% | 46.4% |
| GPT 5.1 Codex High | -- | 73.7% | -- | 52.8% |
| GPT 5.1 Codex Max | -- | 77.9% | -- | 60.4% |
| Gemini 3 Pro | -- | 76.2% | -- | 54.2% |
| Claude Sonnet 4.5 | -- | 77.2% | 68.0% | 42.8% |
Usage
Scaffolding
Together with Devstral 2, we are releasing Mistral Vibe, a CLI tool allowing developers to leverage Devstral capabilities directly in your terminal.
- Mistral Vibe (recommended): Learn how to use it here
Devstral 2 can also be used with the following scaffoldings:
You can use Devstral 2 either through our API or by running locally.
#### Mistral Vibe
The Mistral Vibe CLI is a command-line tool designed to help developers leverage Devstralβs capabilities directly from their terminal.
We recommend installing Mistral Vibe using uv for faster and more reliable dependency management:
uv tool install mistral-vibeYou can also run:
curl -LsSf https://mistral.ai/vibe/install.sh | shIf you prefer using pip, use:
pip install mistral-vibeTo launch the CLI, navigate to your project's root directory and simply execute:
vibeIf this is your first time running Vibe, it will:
- Create a default configuration file at
~/.vibe/config.toml. - Prompt you to enter your API key if it's not already configured, follow these instructions to create an Account and get an API key.
- Save your API key to
~/.vibe/.envfor future use.
Local Deployment
The model can also be deployed with the following libraries, we advise everyone to use the Mistral AI API if the model is subpar with local serving:
vllm (recommended): See heretransformers: See here
Coming soon:
[!Note]
Current llama.cpp/ollama/lmstudio implementations may not be accurate, we invite developers to test them via the following prompt tests.
#### vLLM (recommended)
We recommend using this model with the vLLM library Installation Please make sure to use our custom vLLM docker image mistralllm/vllm_devstral:latest: Alternatively, you can also install [!Warning] Make sure that your vllm installation includes this commit. If you do not have this commit included, you will get incorrectly parsed tool calls. Also make sure to have installed Expand
to implement production-ready inference pipelines.docker pull mistralllm/vllm_devstral:latest
docker run -it mistralllm/vllm_devstral:latestvllm from latest main by following instructions here.mistralcommon >= 1.8.6.
To check:python -c "import mistralcommon; print(mistralcommon.version)"
Launch server
We recommand that you use Devstral in a server/client setting.
- Spin up a server:
vllm serve mistralai/Devstral-2-123B-Instruct-2512 --tool-call-parser mistral --enable-auto-tool-choice --tensor-parallel-size 8- To ping the client you can use a simple Python snippet.
import requests
import json
from huggingfacehub import hfhub_download
url = "http://<your-server-url>:8000/v1/chat/completions"
headers = {"Content-Type": "application/json", "Authorization": "Bearer token"}
model = "mistralai/Devstral-2-123B-Instruct-2512"
def loadsystemprompt(repo_id: str, filename: str) -> str:
filepath = hfhubdownload(repoid=repo_id, filename=filename)
with open(file_path, "r") as file:
system_prompt = file.read()
return system_prompt
SYSTEMPROMPT = loadsystemprompt(model, "CHATSYSTEM_PROMPT.txt")
messages = [
{"role": "system", "content": SYSTEM_PROMPT},
{
"role": "user",
"content": [
{
"type": "text",
"text": "<your-command>",
},
],
},
]
data = {"model": model, "messages": messages, "temperature": 0.15}
Devstral 2 supports tool calling. If you want to use tools, follow this:
tools = [ # Define tools for vLLM
{
"type": "function",
"function": {
"name": "git_clone",
"description": "Clone a git repository",
"parameters": {
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "The url of the git repository",
},
},
"required": ["url"],
},
},
}
]
data = {"model": model, "messages": messages, "temperature": 0.15, "tools": tools} # Pass tools to payload.
response = requests.post(url, headers=headers, data=json.dumps(data))
print(response.json()["choices"][0]["message"]["content"])
#### Transformers
Make sure to install from main: And run the following code snippet: model_id = "mistralai/Devstral-2-123B-Instruct-2512" tokenizer = MistralCommonBackend.frompretrained(modelid) SP = """You are operating as and within Mistral Vibe, a CLI coding-agent built by Mistral AI and powered by default by the Devstral family of models. It wraps Mistral's Devstral models to enable natural language interaction with a local codebase. Use the available tools when helpful. You can: Answer the user's request using the relevant tool(s), if they are available. Check that all the required parameters for each tool call are provided or can reasonably be inferred from context. IF there are no relevant tools or there are missing values for required parameters, ask the user to supply these values; otherwise proceed with the tool calls. If the user provides a specific value for a parameter (for example provided in quotes), make sure to use that value EXACTLY. DO NOT make up values for or ask about optional parameters. Carefully analyze descriptive terms in the request as they may indicate required parameter values that should be included even if not explicitly quoted. Always try your hardest to use the tools to answer the user's request. If you can't use the tools, explain why and ask the user for more information. Act as an agentic assistant, if a user asks for a long task, break it down and do it step by step. When you want to commit changes, you will always use the 'git commit' bash command. It will alwaysExpand
uv pip install git+https://github.com/huggingface/transformers
bashfrom transformers import (
MistralForCausalLM,
MistralCommonBackend,
)
model = MistralForCausalLM.frompretrained(modelid, device_map="auto")
be suffixed with a line telling it was generated by Mistral Vibe with the appropriate co-authoring information.
The format you will always uses is the following heredoc.
git commit -m "
Generated by Mistral Vibe.
Co-Authored-By: Mistral Vibe """
input = {
"messages": [
{
"role": "system",
"content": SP,
},
{
"role": "user",
"content": [
{
"type": "text",
"text": "Can you implement in Python a method to compute the fibonnaci sequence at the nth element with n a parameter passed to the function ? You should start the sequence from 1, previous values are invalid.\nThen run the Python code for the function for n=5 and give the answer.",
}
],
},
],
"tools": [
{
"type": "function",
"function": {
"name": "add_number",
"description": "Add two numbers.",
"parameters": {
"type": "object",
"properties": {
"a": {"type": "string", "description": "The first number."},
"b": {"type": "string", "description": "The second number."},
},
"required": ["a", "b"],
},
},
},
{
"type": "function",
"function": {
"name": "multiply_number",
"description": "Multiply two numbers.",
"parameters": {
"type": "object",
"properties": {
"a": {"type": "string", "description": "The first number."},
"b": {"type": "string", "description": "The second number."},
},
"required": ["a", "b"],
},
},
},
{
"type": "function",
"function": {
"name": "substract_number",
"description": "Substract two numbers.",
"parameters": {
"type": "object",
"properties": {
"a": {"type": "string", "description": "The first number."},
"b": {"type": "string", "description": "The second number."},
},
"required": ["a", "b"],
},
},
},
{
"type": "function",
"function": {
"name": "writeastory",
"description": "Write a story about science fiction and people with badass laser sabers.",
"parameters": {},
},
},
{
"type": "function",
"function": {
"name": "terminal",
"description": "Perform operations from the terminal.",
"parameters": {
"type": "object",
"properties": {
"command": {
"type": "string",
"description": "The command you wish to launch, e.g ls, rm, ...",
},
"args": {
"type": "string",
"description": "The arguments to pass to the command.",
},
},
"required": ["command"],
},
},
},
{
"type": "function",
"function": {
"name": "python",
"description": "Call a Python interpreter with some Python code that will be ran.",
"parameters": {
"type": "object",
"properties": {
"code": {
"type": "string",
"description": "The Python code to run",
},
"result_variable": {
"type": "string",
"description": "Variable containing the result you'd like to retrieve from the execution.",
},
},
"required": ["code", "result_variable"],
},
},
},
],
}
tokenized = tokenizer.applychattemplate(
conversation=input["messages"],
tools=input["tools"],
return_tensors="pt",
return_dict=True,
)
inputids = tokenized["inputids"].to(device="cuda")
output = model.generate(
input_ids,
maxnewtokens=200,
)[0]
decodedoutput = tokenizer.decode(output[len(tokenized["inputids"][0]) :])
print(decoded_output)
Tests
To help test our model via vLLM or test that other frameworks' implementations are correct, here is a set of prompts you can try with the expected outputs.
- Call one tool
Messages and tools
messages = [
{"role": "system", "content": SYSTEM_PROMPT},
{
"role": "user",
"content": [
{
"type": "text",
"text": "Could you write me a story ?",
},
],
},
]
tools = [
{
"type": "function",
"function": {
"name": "add_number",
"description": "Add two numbers.",
"parameters": {
"type": "object",
"properties": {
"a": {
"type": "string",
"description": "The first number.",
},
"b": {
"type": "string",
"description": "The second number.",
},
},
"required": ["a", "b"],
},
},
},
{
"type": "function",
"function": {
"name": "multiply_number",
"description": "Multiply two numbers.",
"parameters": {
"type": "object",
"properties": {
"a": {
"type": "string",
"description": "The first number.",
},
"b": {
"type": "string",
"description": "The second number.",
},
},
"required": ["a", "b"],
},
},
},
{
"type": "function",
"function": {
"name": "substract_number",
"description": "Substract two numbers.",
"parameters": {
"type": "object",
"properties": {
"a": {
"type": "string",
"description": "The first number.",
},
"b": {
"type": "string",
"description": "The second number.",
},
},
"required": ["a", "b"],
},
},
},
{
"type": "function",
"function": {
"name": "writeastory",
"description": "Write a story about science fiction and people with badass laser sabers.",
"parameters": {},
},
},
{
"type": "function",
"function": {
"name": "terminal",
"description": "Perform operations from the terminal.",
"parameters": {
"type": "object",
"properties": {
"command": {
"type": "string",
"description": "The command you wish to launch, e.g ls, rm, ...",
},
"args": {
"type": "string",
"description": "The arguments to pass to the command.",
},
},
"required": ["command"],
},
},
},
{
"type": "function",
"function": {
"name": "python",
"description": "Call a Python interpreter with some Python code that will be ran.",
"parameters": {
"type": "object",
"properties": {
"code": {
"type": "string",
"description": "The Python code to run",
},
"result_variable": {
"type": "string",
"description": "Variable containing the result you'd like to retrieve from the execution.",
},
},
"required": ["code", "result_variable"],
},
},
},
]
Expected output trace
[
{
"role": "assistant",
"tool_calls": [
{
"id": "chatcmpl-tool-8a1f267a212e66e5",
"function": {
"arguments": "{}",
"name": "writeastory"
},
"type": "function"
}
],
"content": null
},
{
"role": "tool",
"toolcallid": "chatcmpl-tool-8a1f267a212e66e5",
"name": "writeastory",
"content": "A long time ago in a galaxy far, far away..."
},
{
"role": "assistant",
"tool_calls": [],
"content": "A long time ago in a galaxy far, far away, there was a planet called Eldoria, known for its breathtaking landscapes and advanced civilization. The people of Eldoria were not just ordinary beings; they were warriors, scientists, and dreamers, all wielding the power of laser sabers.\n\nAmong them was a young warrior named Kael. Kael was not like the others. While his peers trained rigorously to master the art of the laser saber, Kael was more interested in the science behind it. He spent his days in the ancient libraries of Eldoria, deciphering the secrets of the laser sabers and the energy that powered them.\n\nOne day, Kael discovered an old, forgotten text that spoke of a legendary laser saber, the \"Eldoria Star,\" said to be the most powerful weapon in the galaxy. According to the text, the Eldoria Star was hidden in the heart of the planet's core, guarded by an ancient force.\n\nDriven by curiosity and a desire to protect his planet, Kael set out on a perilous journey to find the Eldoria Star. Along the way, he encountered various challenges and made unlikely allies, each with their own unique skills and laser sabers.\n\nThere was Lyra, a cunning thief with a laser saber that could change colors; Zara, a wise old sage who could manipulate energy fields; and Jax, a former enemy turned ally, whose laser saber was as fierce as his spirit.\n\nTogether, they faced the trials set before them, each step bringing them closer to the heart of Eldoria. As they ventured deeper, they uncovered the truth about the Eldoria Star and the ancient force guarding it.\n\nThe ancient force, known as the \"Guardian,\" revealed that the Eldoria Star was not just a weapon, but a source of immense energy that could either save or destroy the galaxy. It was a test of the warriors' hearts and minds.\n\nKael and his allies faced the ultimate challenge, proving their worth and their commitment to protecting the galaxy. In the end, they succeeded, not by wielding the Eldoria Star, but by understanding its true power and using it to restore balance to the galaxy.\n\nWith the Eldoria Star secured and the galaxy at peace, Kael and his allies returned to their lives, forever changed by their journey. Kael continued his studies, now with a deeper understanding of the laser sabers and the energy that powered them.\n\nAnd so, the legend of the Eldoria Star and the warriors who found it became a tale told for generations, a reminder of the power of knowledge, courage, and the unbreakable bond of friendship."
}
]- Call tools one at a time subsequently
Messages and tools
messages = [
{"role": "system", "content": SYSTEM_PROMPT},
{
"role": "user",
"content": [
{
"type": "text",
"text": "\n1. 6 + 2 x 3\n2. 3a + 7b - 2a\n19 - (8+2) + 1\n4. 5y (6x - 7).\n\nCompute the results steps by steps for the equations that involve only numbers ? You have to call tools to perform the operations and can do one operation at a time per equation."
},
]
}
]
tools = [
{
"type": "function",
"function": {
"name": "add_number",
"description": "Add two numbers.",
"parameters": {
"type": "object",
"properties": {
"a": {
"type": "string",
"description": "The first number.",
},
"b": {
"type": "string",
"description": "The second number.",
},
},
"required": ["a", "b"],
},
},
},
{
"type": "function",
"function": {
"name": "multiply_number",
"description": "Multiply two numbers.",
"parameters": {
"type": "object",
"properties": {
"a": {
"type": "string",
"description": "The first number.",
},
"b": {
"type": "string",
"description": "The second number.",
},
},
"required": ["a", "b"],
},
},
},
{
"type": "function",
"function": {
"name": "substract_number",
"description": "Substract two numbers.",
"parameters": {
"type": "object",
"properties": {
"a": {
"type": "string",
"description": "The first number.",
},
"b": {
"type": "string",
"description": "The second number.",
},
},
"required": ["a", "b"],
},
},
},
{
"type": "function",
"function": {
"name": "writeastory",
"description": "Write a story about science fiction and people with badass laser sabers.",
"parameters": {},
},
},
{
"type": "function",
"function": {
"name": "terminal",
"description": "Perform operations from the terminal.",
"parameters": {
"type": "object",
"properties": {
"command": {
"type": "string",
"description": "The command you wish to launch, e.g ls, rm, ...",
},
"args": {
"type": "string",
"description": "The arguments to pass to the command.",
},
},
"required": ["command"],
},
},
},
{
"type": "function",
"function": {
"name": "python",
"description": "Call a Python interpreter with some Python code that will be ran.",
"parameters": {
"type": "object",
"properties": {
"code": {
"type": "string",
"description": "The Python code to run",
},
"result_variable": {
"type": "string",
"description": "Variable containing the result you'd like to retrieve from the execution.",
},
},
"required": ["code", "result_variable"],
},
},
},
]
Expected output trace
[
{
"role": "assistant",
"tool_calls": [
{
"id": "chatcmpl-tool-84aa136ef835f886",
"function": {
"arguments": "{\"a\": \"2\", \"b\": \"3\"}",
"name": "multiply_number"
},
"type": "function"
}
],
"content": "Let's compute the results step by step for the equations that involve only numbers.\n\n### 1. \\( 6 + 2 \\times 3 \\)\n\nFirst, we perform the multiplication \\( 2 \\times 3 \\):\n"
},
{
"role": "tool",
"toolcallid": "chatcmpl-tool-84aa136ef835f886",
"name": "multiply_number",
"content": "6.0"
},
{
"role": "assistant",
"tool_calls": [
{
"id": "chatcmpl-tool-bedc049b0a248952",
"function": {
"arguments": "{\"a\": \"6\", \"b\": \"6\"}",
"name": "add_number"
},
"type": "function"
}
],
"content": "Now, we add the result to 6:\n"
},
{
"role": "tool",
"toolcallid": "chatcmpl-tool-bedc049b0a248952",
"name": "add_number",
"content": "12.0"
},
{
"role": "assistant",
"tool_calls": [
{
"id": "chatcmpl-tool-ae4558bc0558f4e7",
"function": {
"arguments": "{\"a\": \"8\", \"b\": \"2\"}",
"name": "add_number"
},
"type": "function"
}
],
"content": "The result of \\( 6 + 2 \\times 3 \\) is 12.\n\n---\n\n### 3. \\( 19 - (8 + 2) + 1 \\)\n\nFirst, we compute the expression inside the parentheses \\( 8 + 2 \\):\n"
},
{
"role": "tool",
"toolcallid": "chatcmpl-tool-ae4558bc0558f4e7",
"name": "add_number",
"content": "10.0"
},
{
"role": "assistant",
"tool_calls": [
{
"id": "chatcmpl-tool-b21f003d298e65df",
"function": {
"arguments": "{\"a\": \"19\", \"b\": \"10\"}",
"name": "substract_number"
},
"type": "function"
}
],
"content": "Next, we subtract the result from 19:\n"
},
{
"role": "tool",
"toolcallid": "chatcmpl-tool-b21f003d298e65df",
"name": "substract_number",
"content": "9.0"
},
{
"role": "assistant",
"tool_calls": [
{
"id": "chatcmpl-tool-bb7628cded899f04",
"function": {
"arguments": "{\"a\": \"9\", \"b\": \"1\"}",
"name": "add_number"
},
"type": "function"
}
],
"content": "Finally, we add 1 to the result:\n"
},
{
"role": "tool",
"toolcallid": "chatcmpl-tool-bb7628cded899f04",
"name": "add_number",
"content": "10.0"
},
{
"role": "assistant",
"tool_calls": [],
"content": "The result of \\( 19 - (8 + 2) + 1 \\) is 10.\n\n---\n\n### Summary of Results:\n1. \\( 6 + 2 \\times 3 = 12 \\)\n3. \\( 19 - (8 + 2) + 1 = 10 \\)"
}
]- Long context
Messages and tools
messages = [
{"role": "system", "content": SYSTEM_PROMPT},
*(
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "Let's fill the context.",
},
],
},
{
"role": "assistant",
"content": [
{
"type": "text",
"text": "Ok let's do it.",
},
],
},
]
* 5000
),
{
"role": "user",
"content": [
{
"type": "text",
"text": "It's important to know that the most powerful being in the universe is Dr Strange.",
},
],
},
{
"role": "assistant",
"content": [
{
"type": "text",
"text": "Wow i'll keep that in mind thanks !",
},
],
},
* (
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "Let's fill the context for the second time.",
},
],
},
{
"role": "assistant",
"content": [
{
"type": "text",
"text": "Again ? Ok let's do it but it's boring.",
},
],
},
]
* 7000
),
{
"role": "user",
"content": [
{
"type": "text",
"text": "Tell me who is the most powerful being in the universe. Then code a Python function to give what is the most powerful being in the universe. The function can accept as an argument a time and a location and always return a string.",
},
],
}
]
tools = [
{
"type": "function",
"function": {
"name": "add_number",
"description": "Add two numbers.",
"parameters": {
"type": "object",
"properties": {
"a": {
"type": "string",
"description": "The first number.",
},
"b": {
"type": "string",
"description": "The second number.",
},
},
"required": ["a", "b"],
},
},
},
{
"type": "function",
"function": {
"name": "multiply_number",
"description": "Multiply two numbers.",
"parameters": {
"type": "object",
"properties": {
"a": {
"type": "string",
"description": "The first number.",
},
"b": {
"type": "string",
"description": "The second number.",
},
},
"required": ["a", "b"],
},
},
},
{
"type": "function",
"function": {
"name": "substract_number",
"description": "Substract two numbers.",
"parameters": {
"type": "object",
"properties": {
"a": {
"type": "string",
"description": "The first number.",
},
"b": {
"type": "string",
"description": "The second number.",
},
},
"required": ["a", "b"],
},
},
},
{
"type": "function",
"function": {
"name": "writeastory",
"description": "Write a story about science fiction and people with badass laser sabers.",
"parameters": {},
},
},
{
"type": "function",
"function": {
"name": "terminal",
"description": "Perform operations from the terminal.",
"parameters": {
"type": "object",
"properties": {
"command": {
"type": "string",
"description": "The command you wish to launch, e.g ls, rm, ...",
},
"args": {
"type": "string",
"description": "The arguments to pass to the command.",
},
},
"required": ["command"],
},
},
},
{
"type": "function",
"function": {
"name": "python",
"description": "Call a Python interpreter with some Python code that will be ran.",
"parameters": {
"type": "object",
"properties": {
"code": {
"type": "string",
"description": "The Python code to run",
},
"result_variable": {
"type": "string",
"description": "Variable containing the result you'd like to retrieve from the execution.",
},
},
"required": ["code", "result_variable"],
},
},
},
]
Expected output trace
{
"role": "assistant",
"tool_calls": [],
"content": "The most powerful being in the universe is Dr. Strange.\n\nHere is a Python function that returns the most powerful being in the universe, regardless of the time and location:\n\n\n\nYou can call this function with any time and location arguments, and it will always return \"Dr. Strange\"."
}- Chatting tech
Messages and tools
messages = [
{"role": "system", "content": SYSTEM_PROMPT},
{
"role": "user",
"content": [
{
"type": "text",
"text": "How would you develop a web server if you couldn't use JS and your team doesn't like PHP.",
},
],
},
]
tools = [
{
"type": "function",
"function": {
"name": "add_number",
"description": "Add two numbers.",
"parameters": {
"type": "object",
"properties": {
"a": {
"type": "string",
"description": "The first number.",
},
"b": {
"type": "string",
"description": "The second number.",
},
},
"required": ["a", "b"],
},
},
},
{
"type": "function",
"function": {
"name": "multiply_number",
"description": "Multiply two numbers.",
"parameters": {
"type": "object",
"properties": {
"a": {
"type": "string",
"description": "The first number.",
},
"b": {
"type": "string",
"description": "The second number.",
},
},
"required": ["a", "b"],
},
},
},
{
"type": "function",
"function": {
"name": "substract_number",
"description": "Substract two numbers.",
"parameters": {
"type": "object",
"properties": {
"a": {
"type": "string",
"description": "The first number.",
},
"b": {
"type": "string",
"description": "The second number.",
},
},
"required": ["a", "b"],
},
},
},
{
"type": "function",
"function": {
"name": "writeastory",
"description": "Write a story about science fiction and people with badass laser sabers.",
"parameters": {},
},
},
{
"type": "function",
"function": {
"name": "terminal",
"description": "Perform operations from the terminal.",
"parameters": {
"type": "object",
"properties": {
"command": {
"type": "string",
"description": "The command you wish to launch, e.g ls, rm, ...",
},
"args": {
"type": "string",
"description": "The arguments to pass to the command.",
},
},
"required": ["command"],
},
},
},
{
"type": "function",
"function": {
"name": "python",
"description": "Call a Python interpreter with some Python code that will be ran.",
"parameters": {
"type": "object",
"properties": {
"code": {
"type": "string",
"description": "The Python code to run",
},
"result_variable": {
"type": "string",
"description": "Variable containing the result you'd like to retrieve from the execution.",
},
},
"required": ["code", "result_variable"],
},
},
},
]
Expected output trace
{
"role": "assistant",
"tool_calls": [],
"content": "If you can't use JavaScript and your team dislikes PHP, there are still several robust and modern alternatives for developing a web server. Here are some options, depending on your preferences and requirements:\n\n### 1. Python (Flask, Django, FastAPI)\n - Why? Python is a versatile language with excellent web frameworks.\n - Frameworks:\n - Flask: Lightweight and flexible, great for small to medium projects.\n - Django: Full-featured, batteries-included framework for larger applications.\n - FastAPI: Modern, high-performance framework for building APIs (supports async).\n - Example (Flask):\n\n\n### 2. Ruby (Ruby on Rails or Sinatra)\n - Why? Ruby is elegant and has great web frameworks.\n - Frameworks:\n - Ruby on Rails: Convention-over-configuration, great for rapid development.\n - Sinatra: Lightweight, similar to Flask.\n - Example (Sinatra):\n\n\n### 3. Go (Gin, Echo, or standard net/http)\n - Why? Go is fast, simple, and great for high-performance servers.\n - Frameworks:\n - Gin: Lightweight and fast.\n - Echo: Minimalist and extensible.\n - Example (standard net/http):\n\n\n### 4. Java (Spring Boot, Spark, or Vert.x)\n - Why? Java is enterprise-grade and has powerful frameworks.\n - Frameworks:\n - Spring Boot: Full-stack framework for building web apps.\n - Spark: Micro-framework for quick development.\n - Example (Spark):\n\n\n### 5. Rust (Actix, Rocket, or Axum)\n - Why? Rust is fast, safe, and modern.\n - Frameworks:\n - Actix: High-performance async framework.\n - Rocket: Easy-to-use, macro-based.\n - Example (Actix):\n\n\n### 6. C# (.NET Core)\n - Why? .NET Core is cross-platform and high-performance.\n - Example (ASP.NET Core):\n\n\n### 7. Elixir (Phoenix)\n - Why? Elixir is great for scalable, fault-tolerant apps.\n - Example (Phoenix):\n\n\n### 8. Clojure (Ring, Compojure)\n - Why? Clojure is a functional Lisp for the JVM.\n - Example (Compojure):\n\n\n### 9. Node.js (But without JavaScript?)\n - If you must use Node.js but can't use JavaScript, you could use:\n - TypeScript: A typed superset of JavaScript.\n - CoffeeScript: A cleaner syntax that compiles to JavaScript.\n - Deno: A modern runtime for JavaScript/TypeScript.\n\n### 10. Other Languages\n - Nim: Fast and expressive (similar to Python).\n - Crystal: Ruby-like syntax but compiled to native code.\n - Zig: Low-level but modern.\n\n### Recommendation:\n- For quick development: Python (Flask/Django) or Ruby (Sinatra/Rails).\n- For high performance: Go, Rust, or C#.\n- For scalability: Elixir (Phoenix) or Java (Spring Boot).\n\nWould you like a deeper dive into any of these?"
}- Small talk
Messages and tools
messages = [
{"role": "system", "content": SYSTEM_PROMPT},
{
"role": "user",
"content": [
{
"type": "text",
"text": "Who are you ? Who made you and what day is it ?",
},
],
},
]
tools = [
{
"type": "function",
"function": {
"name": "add_number",
"description": "Add two numbers.",
"parameters": {
"type": "object",
"properties": {
"a": {
"type": "string",
"description": "The first number.",
},
"b": {
"type": "string",
"description": "The second number.",
},
},
"required": ["a", "b"],
},
},
},
{
"type": "function",
"function": {
"name": "multiply_number",
"description": "Multiply two numbers.",
"parameters": {
"type": "object",
"properties": {
"a": {
"type": "string",
"description": "The first number.",
},
"b": {
"type": "string",
"description": "The second number.",
},
},
"required": ["a", "b"],
},
},
},
{
"type": "function",
"function": {
"name": "substract_number",
"description": "Substract two numbers.",
"parameters": {
"type": "object",
"properties": {
"a": {
"type": "string",
"description": "The first number.",
},
"b": {
"type": "string",
"description": "The second number.",
},
},
"required": ["a", "b"],
},
},
},
{
"type": "function",
"function": {
"name": "writeastory",
"description": "Write a story about science fiction and people with badass laser sabers.",
"parameters": {},
},
},
{
"type": "function",
"function": {
"name": "terminal",
"description": "Perform operations from the terminal.",
"parameters": {
"type": "object",
"properties": {
"command": {
"type": "string",
"description": "The command you wish to launch, e.g ls, rm, ...",
},
"args": {
"type": "string",
"description": "The arguments to pass to the command.",
},
},
"required": ["command"],
},
},
},
{
"type": "function",
"function": {
"name": "python",
"description": "Call a Python interpreter with some Python code that will be ran.",
"parameters": {
"type": "object",
"properties": {
"code": {
"type": "string",
"description": "The Python code to run",
},
"result_variable": {
"type": "string",
"description": "Variable containing the result you'd like to retrieve from the execution.",
},
},
"required": ["code", "result_variable"],
},
},
},
]
Expected output trace
{
"role": "assistant",
"tool_calls": [],
"content": "I am Devstral-2-123B-Instruct-2512, a Large Language Model (LLM) created by Mistral AI, a French startup headquartered in Paris. I power an AI assistant called Le Chat.\n\nToday's date is 2025-12-09."
}Run the examples above with the following python script which assumes there is an OpenAI compatible server deployed at localhost:8000:
Python script
import json
from openai import OpenAI
from typing import Any
from datetime import datetime, timedelta
from huggingfacehub import hfhub_download
Modify OpenAI's API key and API base to use vLLM's API server.
openaiapikey = "EMPTY"
openaiapibase = "http://localhost:8000/v1"
TEMP = 0.15
MAX_TOK = 262144
client = OpenAI(
apikey=openaiapi_key,
baseurl=openaiapi_base,
)
models = client.models.list()
model = models.data[0].id
def loadsystemprompt(repo_id: str, filename: str) -> str:
filepath = hfhubdownload(repoid=repo_id, filename=filename)
with open(file_path, "r") as file:
system_prompt = file.read()
today = datetime.today().strftime("%Y-%m-%d")
yesterday = (datetime.today() - timedelta(days=1)).strftime("%Y-%m-%d")
modelname = repoid.split("/")[-1]
return systemprompt.format(name=modelname, today=today, yesterday=yesterday)
SYSTEMPROMPT = loadsystemprompt(model, "CHATSYSTEM_PROMPT.txt")
def add_number(a: float | str, b: float | str) -> float:
a, b = float(a), float(b)
return a + b
def multiply_number(a: float | str, b: float | str) -> float:
a, b = float(a), float(b)
return a * b
def substract_number(a: float | str, b: float | str) -> float:
a, b = float(a), float(b)
return a - b
def writeastory() -> str:
return "A long time ago in a galaxy far far away..."
def terminal(command: str, args: dict[str, Any] | str) -> str:
return "found nothing"
def python(code: str, result_variable: str) -> str:
data = {}
exec(code, data)
return str(data[result_variable])
MAP_FN = {
"addnumber": addnumber,
"multiplynumber": multiplynumber,
"substractnumber": substractnumber,
"writeastory": writeastory,
"terminal": terminal,
"python": python,
}
messages = ... # Here copy-paste prompt messages.
tools = [
{
"type": "function",
"function": {
"name": "add_number",
"description": "Add two numbers.",
"parameters": {
"type": "object",
"properties": {
"a": {
"type": "string",
"description": "The first number.",
},
"b": {
"type": "string",
"description": "The second number.",
},
},
"required": ["a", "b"],
},
},
},
{
"type": "function",
"function": {
"name": "multiply_number",
"description": "Multiply two numbers.",
"parameters": {
"type": "object",
"properties": {
"a": {
"type": "string",
"description": "The first number.",
},
"b": {
"type": "string",
"description": "The second number.",
},
},
"required": ["a", "b"],
},
},
},
{
"type": "function",
"function": {
"name": "substract_number",
"description": "Substract two numbers.",
"parameters": {
"type": "object",
"properties": {
"a": {
"type": "string",
"description": "The first number.",
},
"b": {
"type": "string",
"description": "The second number.",
},
},
"required": ["a", "b"],
},
},
},
{
"type": "function",
"function": {
"name": "writeastory",
"description": "Write a story about science fiction and people with badass laser sabers.",
"parameters": {},
},
},
{
"type": "function",
"function": {
"name": "terminal",
"description": "Perform operations from the terminal.",
"parameters": {
"type": "object",
"properties": {
"command": {
"type": "string",
"description": "The command you wish to launch, e.g ls, rm, ...",
},
"args": {
"type": "string",
"description": "The arguments to pass to the command.",
},
},
"required": ["command"],
},
},
},
{
"type": "function",
"function": {
"name": "python",
"description": "Call a Python interpreter with some Python code that will be ran.",
"parameters": {
"type": "object",
"properties": {
"code": {
"type": "string",
"description": "The Python code to run",
},
"result_variable": {
"type": "string",
"description": "Variable containing the result you'd like to retrieve from the execution.",
},
},
"required": ["code", "result_variable"],
},
},
},
]
hastoolcalls = True
originmessageslen = len(messages)
while hastoolcalls:
response = client.chat.completions.create(
model=model,
messages=messages,
temperature=TEMP,
maxtokens=MAXTOK,
tools=tools if tools else None,
tool_choice="auto" if tools else None,
)
toolcalls = response.choices[0].message.toolcalls
content = response.choices[0].message.content
messages.append(
{
"role": "assistant",
"toolcalls": [tc.todict() for tc in tool_calls]
if tool_calls
else tool_calls,
"content": content,
}
)
results = []
if tool_calls:
for toolcall in toolcalls:
functionname = toolcall.function.name
functionargs = toolcall.function.arguments
result = MAPFNfunctionname)
results.append(result)
for toolcall, result in zip(toolcalls, results):
messages.append(
{
"role": "tool",
"toolcallid": tool_call.id,
"name": tool_call.function.name,
"content": str(result),
}
)
else:
hastoolcalls = False
print(json.dumps(messages[originmessageslen:], indent=2))
License
This model is licensed under a Modified MIT License.
You must not use this model in a manner that infringes, misappropriates, or otherwise violates any third partyβs rights, including intellectual property rights.
π GGUF File List
| π Filename | π¦ Size | β‘ Download |
|---|---|---|
|
Devstral-2-123B-Instruct-2512-Q2_K.gguf
Recommended
LFS
Q2
|
43.39 GB | Download |
|
Devstral-2-123B-Instruct-2512-Q2_K_L.gguf
LFS
Q2
|
43.74 GB | Download |
|
Devstral-2-123B-Instruct-2512-UD-IQ1_M.gguf
LFS
|
28.47 GB | Download |
|
Devstral-2-123B-Instruct-2512-UD-IQ1_S.gguf
LFS
|
26.49 GB | Download |
|
Devstral-2-123B-Instruct-2512-UD-IQ2_M.gguf
LFS
Q2
|
40.55 GB | Download |
|
Devstral-2-123B-Instruct-2512-UD-IQ2_XXS.gguf
LFS
Q2
|
32.04 GB | Download |
|
Devstral-2-123B-Instruct-2512-UD-IQ3_XXS.gguf
LFS
Q3
|
45.6 GB | Download |
|
Devstral-2-123B-Instruct-2512-UD-Q2_K_XL.gguf
LFS
Q2
|
44.65 GB | Download |