You can deploy this model and start earning money today!

axolotl-ai-co/
Mistral-Medium-3.5-128B-BF16

Name: Mistral-Medium-3.5-128B-BF16
Availability: InStock

safetensors

mistral3

vLLM

Views

No views yet

Mistral Medium 3.5

This model is a dense one of 128B parameters, including vision:

able to perform instruct, reasoning and agentic tasks.
architecture is the same as Mistral 3 with yarn rope.
the way to trigger reasoning is the same as Mistral Small 4 which is to pass reasoning_effort="high" for reasoning and reasoning_effort="none" for instruct.
context length of 256k

Expect:

gap of performance in comparison with Mistral Small 4 for instruct reasoning and agentic tasks. Can replace Devstral 2 for agentic.
a known limitation is still a multimodal performance subpar with the competition.

Recommended Settings

Reasoning Effort:
- 'none' → Do not use reasoning
- 'high' → Use reasoning (recommended for complex prompts) Use reasoning_effort="high" for complex tasks
Temperature: 0.7 for reasoning_effort="high". Temp between 0.0 and 0.7 for reasoning_effort="none" depending on task.

Use Cases

Mistral Small 4 is designed for general chat assistants, coding, agentic tasks, and reasoning tasks (with reasoning mode toggled). Its multimodal capabilities also enable document and image understanding for data extraction and analysis.

Its capabilities are ideal for:

Developers interested in coding and agentic capabilities for SWE automation and codebase exploration.
Enterprises seeking general chat assistants, agents, and document understanding.
Researchers leveraging its math and research capabilities.

Mistral Small 4 is also well-suited for customization and fine-tuning for more specialized tasks.

Examples

General chat assistant
Document parsing and extraction
Coding agent
Research assistant
Customization & fine-tuning
And more...

Usage

vLLM

We recommend using Mistral Medium 3.5 with the vLLM library for production-ready inference.

Installation

[!Tip] Use our custom Docker image with fixes for tool calling and reasoning parsing in vLLM, and the latest Transformers version. We are working with the vLLM team to merge these fixes soon.

Custom Docker Use the following Docker image: mistralllm/vllm-ms4:latest:

bash

docker pull mistralllm/vllm-ms4:latest
docker run -it mistralllm/vllm-ms4:latest

Manual Install Alternatively, install vllm from this PR: Add Mistral Guidance.

Note: This PR is expected to be merged into vllm main in the next 1-2 weeks (as of 16.03.2026). Track updates here.

Install vLLM:

uv pip install vllm
Install transformers from main:

uv pip install git+https://github.com/huggingface/transformers.git

Ensure mistral_common >= 1.10.0 is installed:

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

Serve the Model

We recommend a server/client setup:

bash

vllm serve mistralai/Mistral-Medium-3.5-128B-2604 --max-model-len 262144 --tensor-parallel-size 8 \
  --tool-call-parser mistral --enable-auto-tool-choice --reasoning-parser mistral --max_num_batched_tokens 16384 --max_num_seqs 128 \
  --gpu_memory_utilization 0.8

Ping the Server

Instruction Following

Mistral Medium 3.5 can follow your instructions to the letter.

python

from datetime import datetime, timedelta

from openai import OpenAI
from huggingface_hub import hf_hub_download

# Modify OpenAI's API key and API base to use vLLM's API server.
openai_api_key = "EMPTY"
openai_api_base = "http://localhost:8000/v1"

TEMP = 0.1
# use TEMP = 0.7 for reasoning="high"

client = OpenAI(
    api_key=openai_api_key,
    base_url=openai_api_base,
)

models = client.models.list()
model = models.data[0].id


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")

messages = [
    {"role": "system", "content": SYSTEM_PROMPT},
    {
        "role": "user",
        "content": "Write me a sentence where every word starts with the next letter in the alphabet - start with 'a' and end with 'z'.",
    },
]

response = client.chat.completions.create(
    model=model,
    messages=messages,
    temperature=TEMP,
    reasoning_effort="none",
)

assistant_message = response.choices[0].message.content
print(assistant_message)

Tool Call

Let's solve some equations thanks to our simple Python calculator tool.

python

import json
from datetime import datetime, timedelta

from openai import OpenAI
from huggingface_hub import hf_hub_download

# Modify OpenAI's API key and API base to use vLLM's API server.
openai_api_key = "EMPTY"
openai_api_base = "http://localhost:8000/v1"

TEMP = 0.1

client = OpenAI(
    api_key=openai_api_key,
    base_url=openai_api_base,
)

models = client.models.list()
model = models.data[0].id


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://math-coaching.com/img/fiche/46/expressions-mathematiques.jpg"


def my_calculator(expression: str) -> str:
    return str(eval(expression))


tools = [
    {
        "type": "function",
        "function": {
            "name": "my_calculator",
            "description": "A calculator that can evaluate a mathematical expression.",
            "parameters": {
                "type": "object",
                "properties": {
                    "expression": {
                        "type": "string",
                        "description": "The mathematical expression to evaluate.",
                    },
                },
                "required": ["expression"],
            },
        },
    },
    {
        "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": [
            {
                "type": "text",
                "text": "Thanks to your calculator, compute the results for the equations that involve numbers displayed in the image.",
            },
            {
                "type": "image_url",
                "image_url": {
                    "url": image_url,
                },
            },
        ],
    },
]

response = client.chat.completions.create(
    model=model,
    messages=messages,
    temperature=TEMP,
    tools=tools,
    tool_choice="auto",
    reasoning_effort="none",
)

tool_calls = response.choices[0].message.tool_calls

results = []
for tool_call in tool_calls:
    function_name = tool_call.function.name
    function_args = tool_call.function.arguments
    if function_name == "my_calculator":
        result = my_calculator(**json.loads(function_args))
        results.append(result)

messages.append({"role": "assistant", "tool_calls": tool_calls})
for tool_call, result in zip(tool_calls, results):
    messages.append(
        {
            "role": "tool",
            "tool_call_id": tool_call.id,
            "name": tool_call.function.name,
            "content": result,
        }
    )


response = client.chat.completions.create(
    model=model,
    messages=messages,
    temperature=TEMP,
    reasoning_effort="none",
)

print(response.choices[0].message.content)

Vision Reasoning

Let's see if the Mistral Medium 3.5 knows when to pick a fight !

python

from datetime import datetime, timedelta

from openai import OpenAI
from huggingface_hub import hf_hub_download

# Modify OpenAI's API key and API base to use vLLM's API server.
openai_api_key = "EMPTY"
openai_api_base = "http://localhost:8000/v1"

TEMP = 0.7

client = OpenAI(
    api_key=openai_api_key,
    base_url=openai_api_base,
)

models = client.models.list()
model = models.data[0].id


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://static.wikia.nocookie.net/essentialsdocs/images/7/70/Battle.png/revision/latest?cb=20220523172438"

messages = [
    {"role": "system", "content": SYSTEM_PROMPT},
    {
        "role": "user",
        "content": [
            {
                "type": "text",
                "text": "What action do you think I should take in this situation? List all the possible actions and explain why you think they are good or bad.",
            },
            {"type": "image_url", "image_url": {"url": image_url}},
        ],
    },
]


response = client.chat.completions.create(
    model=model,
    messages=messages,
    temperature=TEMP,
    reasoning_effort="high",
)

print(response.choices[0].message.content)

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 party’s rights, including intellectual property rights.

axolotl-ai-co/Mistral-Medium-3.5-128B-BF16

Mistral Medium 3.5

Recommended Settings

Use Cases

Examples

Usage

vLLM

Installation

Serve the Model

Ping the Server

License

axolotl-ai-co/
Mistral-Medium-3.5-128B-BF16