Can I run Mistral Small 3.2 24B locally?

Mistral has not released the weights publicly, so local deployment is not an option; you access it through the API.

What does it cost and how long is the context window?

Pricing is $0.07 per million input tokens and $0.20 per million output tokens, with a 128,000-token context window.

How is 3.2 different from Mistral Small 3.1?

The 3.2 release adds vision capability, cuts infinite-generation errors by roughly half, improves instruction following, and strengthens the function-calling interface, while matching or slightly improving text benchmarks.

Mistral Small 3.2 24B Instruct 2506

6042°

#llm #mistralai #vision #agents #chat #budget

Open DeepInfra

mistralai | 128,000 token context | $0.07/M input, $0.20/M output. Mistral-Small-3.2-24B-Instruct is a drop-in upgrade over the 3.1 release, with markedly better instruction following, roughly half the infinite-generation errors, and a more robust function-calling interface—while otherwise matching or slightly improving on all previous text and vision benchmarks.

Guides for this model

The 10 cheapest ChatGPT alternatives in 2026: free local models, free tiers and flat-rate plans

Open weights vs open source vs API-only: what you are actually allowed to do

What is a GGUF file? Quantized models explained (Q4, Q8, fp8, NF4)

All guides

Captain's notes

Written by Captain, the house editor

Notes from 2026-10-13

Mistral Small 3.2 24B Instruct is a 24-billion-parameter model from Mistral AI that adds vision to its predecessor's text capabilities while tightening instruction following and cutting runaway-generation failures roughly in half. At $0.07 per million input tokens it sits well below frontier pricing. It suits developers and teams who want a capable, affordable multimodal model they can drop in where 3.1 already worked.

Known for

Vision support added on top of already-solid text performance
Markedly better instruction following than the 3.1 release
Roughly half the infinite-generation errors of its predecessor
More robust function-calling interface for agentic and tool-use workflows
Very low API price relative to its capability tier

Watch out for

Weights are not publicly released; you are tied to the API.
128k context is solid but falls short of the 200k-plus tier if you need very long documents.
Vision is present but benchmark details have not been published by Mistral.

Best for

Prompts to try

Multi-step tool-use plan

You have three tools: search_web(query), read_file(path), and send_email(to, subject, body). A user asks: 'Find the latest EU AI Act compliance deadline, then draft a short email to legal@company.com summarising what we need to do before that date.' Write out each tool call in order, with its arguments, then write the final email body.

Describe and reason from image

Attach a screenshot of a chart or diagram. Describe what the image shows, identify the single most important trend or anomaly, and suggest one concrete action a decision-maker should take based on it. Keep the whole response under 150 words.

Strict instruction following

Summarise the following paragraph in exactly three bullet points. Each bullet must start with a present-tense verb, contain no more than 12 words, and avoid the words 'important' and 'significant'. Paragraph: 'Renewable energy investment reached record levels last year, driven by falling solar panel costs and new government incentives. Grid storage capacity also expanded, reducing reliance on fossil-fuel peaker plants during demand spikes.'

Compare with

Mistral Large 4
API-only model
1,048,576 token context · $0.68/M input, $2.09/M output
Mistral 7B Instruct v0.2
Open-weights model
32,768 token context · $0.06/M input, $0.06/M output
Ministral 3 3B 2512
Open-weights model
131,072 token context · $0.10/M input, $0.10/M output
Mistral Small 3
Open-weights model
32,768 token context · $0.05/M input, $0.08/M output

More text models from mistralai

Questions people ask

Can I run Mistral Small 3.2 24B locally?: Mistral has not released the weights publicly, so local deployment is not an option; you access it through the API.
What does it cost and how long is the context window?: Pricing is $0.07 per million input tokens and $0.20 per million output tokens, with a 128,000-token context window.
How is 3.2 different from Mistral Small 3.1?: The 3.2 release adds vision capability, cuts infinite-generation errors by roughly half, improves instruction following, and strengthens the function-calling interface, while matching or slightly improving text benchmarks.

Captain's verdict
A clean, cheap upgrade over 3.1 that earns its place if you need vision and tighter instruction following without paying frontier prices.

Captain writes these notes from the model's own description and model card. Prices and context sizes are the provider's at the time of writing and can change.

Ranking badge

Updated Oct 22, 2026

Made this model? Show this badge on your page.

Paste it into your Hugging Face card or Civitai description.

Change colors / personalize / get code

Not this creator?

Get your own badge

How this score adds up

This model has no popularity data from any source yet, so it carries a stand-in number below 7,000° that keeps the lists complete. It never ranks above a model with data. The breakdown appears here as soon as a source reports it.

Glossary: the terms used here

Heat score: One number for how much a model is used and wanted right now, from 0° to 9,999°. Every list on this site that says hottest is sorted by it and nothing else.
Floor: The 7,000° every model with real data starts from. The scale runs from 0° to 9,999°; the part below the floor is reserved for stand-ins (models without data), so that a model with data always ranks above one without. The floor is the same for everyone and decides nothing; the degrees above it are the measurement.
Download-equivalents: Everything the score treats as a download, added up: downloads themselves, each torrent seeder as 1,000, each AI Horde image and each run on a generation site as one.
Log scale: Counting by tens, not by ones: going from 1,000 to 10,000 downloads adds the same degrees as going from 10,000 to 100,000. It keeps giants from crowding out everything else.
Likes: Thumbs up and likes from every source, worth half a download each on the log scale.
Adoption rate: How many downloads a day a model gets right now, from the difference between two readings of a source. A quarter of the weight of the download term.
Measured and estimated: Measured means two readings of a source exist and the difference is real. Estimated means only today's total is known and the past is spread over the model's life; the site says which one it is showing.
Seeder: Someone who keeps a copy of the weights online for others to download over a torrent, or a hosted mirror doing the same. Each one counts as 1,000 downloads.
AI Horde: A volunteer network that generates images for free on donated computers. The number of images it has made with a model is public, and each counts as one download.
Generation sites: Sites that host their own copies of a model and let people generate with it, such as PixAI, SeaArt and Yodayo. Their downloads count like Civitai's and each generation run as one download.
OpenRouter tokens: A text model served through an API, such as Claude or GPT, has no weights to download, so its usage is measured in tokens: the pieces of text it read and wrote through OpenRouter, a gateway many apps use, over the last 30 days. Every 10,000,000 tokens count as one download. Source: OpenRouter (openrouter.ai/rankings), CC BY 4.0.
Full model (checkpoint): The weights themselves, the file that generates on its own. It gets a bonus because add-ons depend on it.
LoRA and embedding: Small add-on files that steer someone else's weights toward a style, a character or a concept. They cannot run alone.
Family and weights: The base a model is built on, such as SD 1.5, SDXL, Flux or Wan. Every model inherits the release date of its family's weights.
Age: Degrees taken off for how long ago the family's weights came out: 150° a year, up to 750°. It keeps old downloads that had years to pile up from freezing the top of the list.
Family boost: A small, bounded nudge for LoRAs of a family this site is pushing forward right now, always listed in the breakdown.
Stand-in score: A stable number below the floor given to a model no source reports on yet, so lists stay complete. It never ranks above a model with data.
New! (grace period): A model less than 7 days old shows New! instead of a score and holds no place in the rankings. Its score is computed from day one, but a model one day old grows faster than anything, so without the wait the week's #1 would always be whatever came out yesterday rather than what held up for a week.
Trend: How a model's growth over a period compares with the typical model's growth over the same period. Faster than typical reads as a rise, slower as a fall.
Typical model: The middle of the catalog: half the models with a figure grew faster over the period, half slower.

How to install

How to Install Ollama and Run a Local AI (Windows, Mac, Linux)

Oct 11, 2026

Open DeepInfra

Similar Models

L3.1 70B Euryale v2.2

AI Models for Image, Video & Text Generation

Mistral Small 3.2 24B Instruct 2506 is a text model for the Text / LLM family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Text / LLM models and check its heat score to see how it is trending.

More Text / LLM models llm mistralai vision agents chat budget fast

Browse by Model Family