%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)
EN
Mistral Small 3.2 24B Instruct 2506 GGUF
Mistral-Small-3.2-24B-Instruct-2506 is a language model, which is a minor version update of Mistral-Small-3.1-24B-Instruct-2503, with significant improvements in instruction following, reducing repetitive errors, and function calls.
Downloads 1,645
Release Time : 6/20/2025
Model Overview
This model is suitable for image-text to text conversion tasks and supports multiple languages, including English, French, German, Spanish, Portuguese, Italian, Japanese, Korean, Russian, Chinese, Arabic, Persian, Indonesian, Malay, Nepali, Polish, Romanian, Serbian, Swedish, Turkish, Ukrainian, Vietnamese, Hindi, and Bengali.
Model Features
Improved instruction following
Small-3.2 performs better in following precise instructions.
Reduced repetitive errors
Small-3.2 reduces the problems of infinite generation or repetitive answers.
Enhanced function call
The function call template of Small-3.2 is more robust.
Multilingual support
Supports multiple languages, including English, French, German, Spanish, Portuguese, Italian, Japanese, Korean, Russian, Chinese, etc.
Visual reasoning ability
Capable of handling image-text to text conversion tasks.
Model Capabilities
Text generation
Instruction following
Function call
Visual reasoning
Multilingual support
Use Cases
Text processing
Text rewriting
Rewrite the given text into a more concise or clearer version.
The rewritten text better meets the user's needs.
Instruction generation
Generate corresponding text or code according to user instructions.
The generated text or code accurately follows the user's instructions.
Visual reasoning
Image description
Generate descriptive text based on the image content.
The generated description accurately reflects the image content.
Visual question answering
Answer questions related to the image content.
The answers are accurate and consistent with the image content.
Function call
Mathematical calculation
Perform mathematical expression calculations through function calls.
The calculation results are accurate.
Data query
Query specific data through function calls.
The returned data is accurate and in the correct format.
🚀 Mistral-Small-3.2-24B-Instruct-2506
Mistral-Small-3.2-24B-Instruct-2506 is a minor update of the Mistral-Small series, offering improvements in instruction following, reducing repetition errors, and enhancing function calling capabilities.
✨ Features
- Instruction following: Small-3.2 is better at following precise instructions.
- Repetition errors: Small-3.2 produces less infinite generations or repetitive answers.
- Function calling: Small-3.2's function calling template is more robust.
📦 Installation
vLLM (recommended)
Make sure to install vLLM >= 0.9.1:
pip install vllm --upgrade
Doing so should automatically install mistral_common >= 1.6.2.
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.
💻 Usage Examples
vLLM (recommended)
Serve
We recommand that you use Mistral-Small-3.2-24B-Instruct-2506 in a server/client setting.
- Spin up a server:
vllm serve mistralai/Mistral-Small-3.2-24B-Instruct-2506 --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-3.2-24B-Instruct-2506 on GPU requires ~55 GB of GPU RAM in bf16 or fp16.
- To ping the client you can use a simple Python snippet. See the following examples.
Vision reasoning
Take leverage of the vision capabilities of Mistral-Small-3.2-24B-Instruct-2506 to take the best choice given a scenario.
Python snippet
```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 = 0.15 MAX_TOK = 131072 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) model_id = "mistralai/Mistral-Small-3.2-24B-Instruct-2506" SYSTEM_PROMPT = load_system_prompt(model_id, "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, max_tokens=MAX_TOK, ) print(response.choices[0].message.content) # In this situation, you are playing a Pokémon game where your Pikachu (Level 42) is facing a wild Pidgey (Level 17). Here are the possible actions you can take and an analysis of each: # 1. **FIGHT**: # - **Pros**: Pikachu is significantly higher level than the wild Pidgey, which suggests that it should be able to defeat Pidgey easily. This could be a good opportunity to gain experience points and possibly items or money. # - **Cons**: There is always a small risk of Pikachu fainting, especially if Pidgey has a powerful move or a status effect that could hinder Pikachu. However, given the large level difference, this risk is minimal. # 2. **BAG**: # - **Pros**: You might have items in your bag that could help in this battle, such as Potions, Poké Balls, or Berries. Using an item could help you capture the Pidgey or heal your Pikachu if needed. # - **Cons**: Using items might not be necessary given the level difference. It could be more efficient to just fight and defeat the Pidgey quickly. # 3. **POKÉMON**: # - **Pros**: You might have another Pokémon in your party that is better suited for this battle or that you want to gain experience. Switching Pokémon could also be a strategic move if you want to train a lower-level Pokémon. # - **Cons**: Switching Pokémon might not be necessary since Pikachu is at a significant advantage. It could also waste time and potentially give Pidgey a turn to attack. # 4. **RUN**: # - **Pros**: Running away could save time and conserve your Pokémon's health and resources. If you are in a hurry or do not need the experience or items, running away is a safe option. # - **Cons**: Running away means you miss out on the experience points and potential items or money that you could gain from defeating the Pidgey. It also means you do not get the chance to capture the Pidgey if you wanted to. # ### Recommendation: # Given the significant level advantage, the best action is likely to **FIGHT**. This will allow you to quickly defeat the Pidgey, gain experience points, and potentially earn items or money. If you are concerned about Pikachu's health, you could use an item from your **BAG** to heal it before or during the battle. Running away or switching Pokémon does not seem necessary in this situation. ```Function calling
Mistral-Small-3.2-24B-Instruct-2506 is excellent at function / tool calling tasks via vLLM.
Python snippet - easy
```python 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 = 0.15 MAX_TOK = 131072 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() return system_prompt model_id = "mistralai/Mistral-Small-3.2-24B-Instruct-2506" SYSTEM_PROMPT = load_system_prompt(model_id, "SYSTEM_PROMPT.txt") image_url = "https://huggingface.co/datasets/patrickvonplaten/random_img/resolve/main/europe.png" tools = [ { "type": "function", "function": { "name": "get_current_population", "description": "Get the up-to-date population of a given country.", "parameters": { "type": "object", "properties": { "country": { "type": "string", "description": "The country to find the population of.", }, "unit": { "type": "string", "description": "The unit for the population.", "enum": ["millions", "thousands"], }, }, "required": ["country", "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": [ { "type": "text", "text": "Can you tell me what is the biggest country depicted on the map?", }, { "type": "image_url", "image_url": { "url": image_url, }, }, ], } ] response = client.chat.completions.create( model=model, messages=messages, temperature=TEMP, max_tokens=MAX_TOK, tools=tools, tool_choice="auto", ) assistant_message = response.choices[0].message.content print(assistant_message) # The biggest country depicted on the map is Russia. messages.extend([ {"role": "assistant", "content": assistant_message}, {"role": "user", "content": "What is the population of that country in millions?"}, ]) response = client.chat.completions.create( model=model, messages=messages, temperature=TEMP, max_tokens=MAX_TOK, tools=tools, tool_choice="auto", ) print(response.choices[0].message.tool_calls) # [ChatCompletionMessageToolCall(id='3e92V6Vfo', function=Function(arguments='{"country": "Russia", "unit": "millions"}', name='get_current_population'), type='function')] ```Python snippet - complex
```python import json 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 = 0.15 MAX_TOK = 131072 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() return system_prompt model_id = "mistralai/Mistral-Small-3.2-24B-Instruct-2506" SYSTEM_PROMPT = load_system_prompt(model_id, "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": "Can you calculate the results for all the equations displayed in the image? Only compute the ones that involve numbers.", }, { "type": "image_url", "image_url": { "url": image_url, }, }, ], }, ] response = client.chat.completions.create( model=model, messages=messages, temperature=TEMP, max_tokens=MAX_TOK, tools=tools, tool_choice="auto", ) tool_calls = response.choices[0].message.tool_calls print(tool_calls) # [ChatCompletionMessageToolCall(id='CyQBSAtGh', function=Function(arguments='{"expression": "6 + 2 * 3"}', name='my_calculator'), type='function'), ChatCompletionMessageToolCall(id='KQqRCqvzc', function=Function(arguments='{"expression": "19 - (8 + 2) + 1"}', name='my_calculator'), type='function')] 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, max_tokens=MAX_TOK, ) print(response.choices[0].message.content) # Here are the results for the equations that involve numbers: # 1. \( 6 + 2 \times 3 = 12 \) # 3. \( 19 - (8 + 2) + 1 = 10 \) # For the other equations, you need to substitute the variables with specific values to compute the results. ```Instruction following
Mistral-Small-3.2-24B-Instruct-2506 will follow your instructions down to the last letter!
Python snippet
```python 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 = 0.15 MAX_TOK = 131072 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() return system_prompt model_id = "mistralai/Mistral-Small-3.2-24B-Instruct-2506" SYSTEM_PROMPT = load_system_prompt(model_id, "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 wit" } ] # The rest of the code seems incomplete in the original, but the structure for using the model to follow instructions is shown. ```📚 Documentation
Benchmark Results
Text
| Model | Wildbench v2 | Arena Hard v2 | IF (Internal; accuracy) |
|---|---|---|---|
| Small 3.1 24B Instruct | 55.6% | 19.56% | 82.75% |
| Small 3.2 24B Instruct | 65.33% | 43.1% | 84.78% |
Infinite Generations
Small 3.2 reduces infinite generations by 2x on challenging, long and repetitive prompts.
| Model | Infinite Generations (Internal; Lower is better) |
|---|---|
| Small 3.1 24B Instruct | 2.11% |
| Small 3.2 24B Instruct | 1.29% |
STEM
| Model | MMLU | MMLU Pro (5 - shot CoT) | MATH | GPQA Main (5 - shot CoT) | GPQA Diamond (5 - shot CoT ) | MBPP Plus - Pass@5 | HumanEval Plus - Pass@5 | SimpleQA (TotalAcc) |
|---|---|---|---|---|---|---|---|---|
| Small 3.1 24B Instruct | 80.62% | 66.76% | 69.30% | 44.42% | 45.96% | 74.63% | 88.99% | 10.43% |
| Small 3.2 24B Instruct | 80.50% | 69.06% | 69.42% | 44.22% | 46.13% | 78.33% | 92.90% | 12.10% |
Vision
| Model | MMMU | Mathvista | ChartQA | DocVQA | AI2D |
|---|---|---|---|---|---|
| Small 3.1 24B Instruct | 64.00% | 68.91% | 86.24% | 94.08% | 93.72% |
| Small 3.2 24B Instruct | 62.50% | 67.09% | 87.4% | 94.86% | 92.91% |
📄 License
This project is licensed under the Apache-2.0 license.
⚠️ Important Note
If you want to learn more about how we process your personal data, please read our Privacy Policy.
💡 Usage Tip
- We recommend using a relatively low temperature, such as
temperature = 0.15.- Make sure to add a system prompt to the model to best tailer it for your needs. If you want to use the model as a general assistant, we recommend to use the one provided in the SYSTEM_PROMPT.txt file.
Clip Vit Large Patch14 336
A large-scale vision-language pretrained model based on the Vision Transformer architecture, supporting cross-modal understanding between images and text
Text-to-Image
Transformers
TransformersC
openai
5.9M
241
Fashion Clip
MIT
FashionCLIP is a vision-language model fine-tuned specifically for the fashion domain based on CLIP, capable of generating universal product representations.
Text-to-Image Transformers English
Transformers EnglishF
patrickjohncyh
3.8M
222
Gemma 3 1b It
Gemma 3 is a lightweight advanced open model series launched by Google, built on the same research and technology as the Gemini models. This model is multimodal, capable of processing both text and image inputs to generate text outputs.
Text-to-Image Transformers
TransformersG
google
2.1M
347
Blip Vqa Base
Bsd-3-clause
BLIP is a unified vision-language pretraining framework, excelling in visual question answering tasks through joint language-image training to achieve multimodal understanding and generation capabilities
Text-to-Image Transformers
TransformersB
Salesforce
1.9M
154
CLIP ViT H 14 Laion2b S32b B79k
MIT
A vision-language model trained on the LAION-2B English dataset based on the OpenCLIP framework, supporting zero-shot image classification and cross-modal retrieval tasks
Text-to-Image
Safetensors
SafetensorsC
laion
1.8M
368
CLIP ViT B 32 Laion2b S34b B79k
MIT
A vision-language model trained on the English subset of LAION-2B using the OpenCLIP framework, supporting zero-shot image classification and cross-modal retrieval
Text-to-Image Safetensors
SafetensorsC
laion
1.1M
112
Pickscore V1
PickScore v1 is a scoring function for text-to-image generation, used to predict human preferences, evaluate model performance, and rank images.
Text-to-Image Transformers
TransformersP
yuvalkirstain
1.1M
44
Owlv2 Base Patch16 Ensemble
Apache-2.0
OWLv2 is a zero-shot text-conditioned object detection model that can localize objects in images through text queries.
Text-to-Image Transformers
TransformersO
google
932.80k
99
Llama 3.2 11B Vision Instruct
Llama 3.2 is a multilingual, multimodal large language model released by Meta, supporting image-to-text and text-to-text conversion tasks with robust cross-modal understanding capabilities.
Text-to-Image Transformers Supports Multiple Languages
Transformers Supports Multiple LanguagesL
meta-llama
784.19k
1,424
Owlvit Base Patch32
Apache-2.0
OWL-ViT is a zero-shot text-conditioned object detection model that can search for objects in images via text queries without requiring category-specific training data.
Text-to-Image Transformers
TransformersO
google
764.95k
129
Featured Recommended AI Models