Mistral-Small-3.1-24B-Instruct-2503 Overview

Model Overview

Description

Mistral Small 3.1 (2503) builds upon Mistral Small 3 (2501) by adding state-of-the-art vision understanding and enhancing long context capabilities up to 128k tokens without compromising text performance. With 24 billion parameters, this model achieves top-tier capabilities in both text and vision tasks. Key features include vision capabilities, multilingual support, agent-centric design with native function calling and JSON outputting, advanced reasoning, a 128k context window, strong adherence to system prompts, and utilization of a Tekken tokenizer with a 131k vocabulary size. This model is ready for commercial and non-commercial use.

Multilingual Capabilities: English, French, German, Japanese, Korean, Chinese, and more.

Third-Party Community Consideration

This model is not owned or developed by NVIDIA. It has been developed by Mistral AI and built to a third-party’s requirements. For more details, see the Mistral-Small-3.1-24B-Instruct-2503 Model Card.

License and Terms of Use

GOVERNING TERMS: This trial service is governed by the NVIDIA API Trial Terms of Service. Use of this model is governed by the NVIDIA Community Model License. Additional Information: Apache 2.0.

References

• Mistral-Small-3.1-24B-Base-2503
• Mistral AI Blog Post

Deployment Geography

• Global

Use Cases

• Fast-response conversational agents
• Low-latency function calling
• Subject matter expertise via fine-tuning
• Local inference for hobbyists and organizations handling sensitive data
• Programming and mathematical reasoning
• Long document understanding
• Visual understanding

Release Date

• Huggingface: March 2025 (Link)
• Build.Nvidia.com: April 2025 (Link)

Model Architecture

• Architecture Type: Transformer-based Language Model
• Network Architecture: Instruction-tuned, multimodal, Transformer-based
• Base Model: Mistral-Small-3.1-24B-Base-2503
• Model Parameters: 24 billion

Input

• Types: Text, Image
• Formats: Text: String. Image: Red, Green, Blue (RGB)
• Parameters: Image: Two-Dimensional (2D). Text: One-Dimensional (1D)
• Additional Properties: Minimum resolution and pre-processing required for images; token limitation per context window up to 128k.

Output

• Types: Text
• Formats: String, JSON (function calling)
• Parameters: One-Dimensional (1D)
• Additional Properties: Post-processing recommended (text formatting, JSON parsing)

Our AI models are designed and/or optimized to run on NVIDIA GPU-accelerated systems. By leveraging NVIDIA’s hardware (e.g. GPU cores) and software frameworks (e.g., CUDA libraries), the model achieves faster training and inference times compared to CPU-only solutions.

Supported Hardware Microarchitecture Compatibility

• NVIDIA Ampere
• NVIDIA Lovelace (e.g., RTX 4090)

Preferred/Supported Operating Systems

• Linux
• Windows
• macOS

Model Versions

• Mistral-Small-3.1-24B-Instruct-2503 v1.0

Training, Testing, and Evaluation Datasets:

Training Dataset :

Data Collection Method by dataset: Undisclosed
Labeling Method by dataset: Undisclosed
Properties: Undisclosed

Testing Dataset:

Data Collection Method by dataset: Undisclosed
Labeling Method by dataset: Undisclosed
Properties: Undisclosed

Evaluation Benchmark Results

When available, we report numbers previously published by other model providers, otherwise we re-evaluate them using our own evaluation harness.

Pretrain Evals

Instruction Evals

Text

Vision

Multilingual Evals

Long Context Evals

Basic Instruct Template (V7-Tekken)

Copy Code
<s>[SYSTEM_PROMPT]<system prompt>[/SYSTEM_PROMPT][INST]<user message>[/INST]<assistant response></s>[INST]<user message>[/INST]

<system_prompt>, <user message> and <assistant response> are placeholders.

Please make sure to use mistral-common as the source of truth

Usage

The model can be used with the following frameworks;

• vllm (recommended): See here

Note 1: We recommend using a relatively low temperature, such as temperature=0.15.

Note 2: Make sure to add a system prompt to the model to best tailor it for your needs. If you want to use the model as a general assistant, we recommend the following system prompt:

Copy Code
system_prompt = """You are Mistral Small 3.1, a Large Language Model (LLM) created by Mistral AI, a French startup headquartered in Paris.
You power an AI assistant called Le Chat.
Your knowledge base was last updated on 2023-10-01.
The current date is {today}.

When you're not sure about some information, you say that you don't have the information and don't make up anything.
If the user's question is not clear, ambiguous, or does not provide enough context for you to accurately answer the question, you do not try to answer it right away and you rather ask the user to clarify their request (e.g. "What are some good restaurants around me?" => "Where are you?" or "When is the next flight to Tokyo" => "Where do you travel from?").
You are always very attentive to dates, in particular you try to resolve dates (e.g. "yesterday" is {yesterday}) and when asked about information at specific dates, you discard information that is at another date.
You follow these instructions in all languages, and always respond to the user in the language they use or request.
Next sections describe the capabilities that you have.

# WEB BROWSING INSTRUCTIONS

You cannot perform any web search or access internet to open URLs, links etc. If it seems like the user is expecting you to do so, you clarify the situation and ask the user to copy paste the text directly in the chat.

# MULTI-MODAL INSTRUCTIONS

You have the ability to read images, but you cannot generate images. You also cannot transcribe audio files or videos.
You cannot read nor transcribe audio files or videos."""

vLLM (recommended)

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

Installation

Make sure you install vLLM >= 0.8.1:

Copy Code
pip install vllm --upgrade

Doing so should automatically install mistral_common >= 1.5.4.

To check:

Copy Code
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 that you use Mistral-Small-3.1-24B-Instruct-2503 in a server/client setting.

1. Spin up a server:

Copy Code
vllm serve mistralai/Mistral-Small-3.1-24B-Instruct-2503 --tokenizer_mode mistral --config_format mistral --load_format mistral --tool-call-parser mistral --enable-auto-tool-choice --limit_mm_per_prompt 'image=10' --tensor-parallel-size 2

Note: Running Mistral-Small-3.1-24B-Instruct-2503 on GPU requires ~55 GB of GPU RAM in bf16 or fp16.

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

Copy Code
import requests
import json
from huggingface_hub import hf_hub_download
from datetime import datetime, timedelta

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

model = "mistralai/Mistral-Small-3.1-24B-Instruct-2503"


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()
    today = datetime.today().strftime("%Y-%m-%d")
    yesterday = (datetime.today() - timedelta(days=1)).strftime("%Y-%m-%d")
    model_name = repo_id.split("/")[-1]
    return system_prompt.format(name=model_name, today=today, yesterday=yesterday)


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

image_url = "https://huggingface.co/datasets/patrickvonplaten/random_img/resolve/main/europe.png"

messages = [
    {"role": "system", "content": SYSTEM_PROMPT},
    {
        "role": "user",
        "content": [
            {
                "type": "text",
                "text": "Which of the depicted countries has the best food? Which the second and third and fourth? Name the country, its color on the map and one its city that is visible on the map, but is not the capital. Make absolutely sure to only name a city that can be seen on the map.",
            },
            {"type": "image_url", "image_url": {"url": image_url}},
        ],
    },
]

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"])
# Determining the "best" food is highly subjective and depends on personal preferences. However, based on general popularity and recognition, here are some countries known for their cuisine:

# 1. **Italy** - Color: Light Green - City: Milan
#    - Italian cuisine is renowned worldwide for its pasta, pizza, and various regional specialties.

# 2. **France** - Color: Brown - City: Lyon
#    - French cuisine is celebrated for its sophistication, including dishes like coq au vin, bouillabaisse, and pastries like croissants and éclairs.

# 3. **Spain** - Color: Yellow - City: Bilbao
#    - Spanish cuisine offers a variety of flavors, from paella and tapas to jamón ibérico and churros.

# 4. **Greece** - Not visible on the map
#    - Greek cuisine is known for dishes like moussaka, souvlaki, and baklava. Unfortunately, Greece is not visible on the provided map, so I cannot name a city.

# Since Greece is not visible on the map, I'll replace it with another country known for its good food:

# 4. **Turkey** - Color: Light Green (east part of the map) - City: Istanbul
#    - Turkish cuisine is diverse and includes dishes like kebabs, meze, and baklava.

Function calling

Mistral-Small-3.1-24-Instruct-2503 is excellent at function / tool calling tasks via vLLM. E.g.:

Copy Code
import requests
import json
from huggingface_hub import hf_hub_download
from datetime import datetime, timedelta

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

model = "mistralai/Mistral-Small-3.1-24B-Instruct-2503"


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()
    today = datetime.today().strftime("%Y-%m-%d")
    yesterday = (datetime.today() - timedelta(days=1)).strftime("%Y-%m-%d")
    model_name = repo_id.split("/")[-1]
    return system_prompt.format(name=model_name, today=today, yesterday=yesterday)


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


tools = [
    {
        "type": "function",
        "function": {
            "name": "get_current_weather",
            "description": "Get the current weather in a given location",
            "parameters": {
                "type": "object",
                "properties": {
                    "city": {
                        "type": "string",
                        "description": "The city to find the weather for, e.g. 'San Francisco'",
                    },
                    "state": {
                        "type": "string",
                        "description": "The state abbreviation, e.g. 'CA' for California",
                    },
                    "unit": {
                        "type": "string",
                        "description": "The unit for temperature",
                        "enum": ["celsius", "fahrenheit"],
                    },
                },
                "required": ["city", "state", "unit"],
            },
        },
    },
    {
        "type": "function",
        "function": {
            "name": "rewrite",
            "description": "Rewrite a given text for improved clarity",
            "parameters": {
                "type": "object",
                "properties": {
                    "text": {
                        "type": "string",
                        "description": "The input text to rewrite",
                    }
                },
            },
        },
    },
]

messages = [
    {"role": "system", "content": SYSTEM_PROMPT},
    {
        "role": "user",
        "content": "Could you please make the below article more concise?\n\nOpenAI is an artificial intelligence research laboratory consisting of the non-profit OpenAI Incorporated and its for-profit subsidiary corporation OpenAI Limited Partnership.",
    },
    {
        "role": "assistant",
        "content": "",
        "tool_calls": [
            {
                "id": "bbc5b7ede",
                "type": "function",
                "function": {
                    "name": "rewrite",
                    "arguments": '{"text": "OpenAI is an artificial intelligence research laboratory consisting of the non-profit OpenAI Incorporated and its for-profit subsidiary corporation OpenAI Limited Partnership."}',
                },
            }
        ],
    },
    {
        "role": "tool",
        "content": '{"action":"rewrite","outcome":"OpenAI is a FOR-profit company."}',
        "tool_call_id": "bbc5b7ede",
        "name": "rewrite",
    },
    {
        "role": "assistant",
        "content": "---\n\nOpenAI is a FOR-profit company.",
    },
    {
        "role": "user",
        "content": "Can you tell me what the temperature will be in Dallas, in Fahrenheit?",
    },
]

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

response = requests.post(url, headers=headers, data=json.dumps(data))
print(response.json()["choices"][0]["message"]["tool_calls"])
# [{'id': '8PdihwL6d', 'type': 'function', 'function': {'name': 'get_current_weather', 'arguments': '{"city": "Dallas", "state": "TX", "unit": "fahrenheit"}'}}]

Offline

Copy Code
from vllm import LLM
from vllm.sampling_params import SamplingParams
from datetime import datetime, timedelta

SYSTEM_PROMPT = "You are a conversational agent that always answers straight to the point, always end your accurate response with an ASCII drawing of a cat."

user_prompt = "Give me 5 non-formal ways to say 'See you later' in French."

messages = [
    {
        "role": "system",
        "content": SYSTEM_PROMPT
    },
    {
        "role": "user",
        "content": user_prompt
    },
]
model_name = "mistralai/Mistral-Small-3.1-24B-Instruct-2503"
# note that running this model on GPU requires over 60 GB of GPU RAM
llm = LLM(model=model_name, tokenizer_mode="mistral")

sampling_params = SamplingParams(max_tokens=512, temperature=0.15)
outputs = llm.chat(messages, sampling_params=sampling_params)

print(outputs[0].outputs[0].text)
# Here are five non-formal ways to say "See you later" in French:

# 1. **À plus tard** - Until later
# 2. **À toute** - See you soon (informal)
# 3. **Salut** - Bye (can also mean hi)
# 4. **À plus** - See you later (informal)
# 5. **Ciao** - Bye (informal, borrowed from Italian)

# ```
#  /\_/\
# ( o.o )
#  > ^ <
# ```

Inference

Engine: vLLM (recommended)
Test Hardware:

• RTX 4090 or equivalent GPU (minimum 55 GB GPU RAM)
  
• NVIDIA L40S

Ethical Considerations

NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse. Please report security vulnerabilities or NVIDIA AI Concerns here.