Can I run Ministral 3 8B locally?

Yes — the weights are open under Apache 2.0 and available on Hugging Face. Mistral says it fits in 12 GB of VRAM in FP8, and less if you quantise further.

What does it cost via API, and how long is the context?

Pricing is $0.15 per million tokens for both input and output, with a 262,144-token context window.

How does the 8B differ from the 3B in the same family?

The 8B model has a larger 8.4B language model compared to the 3B variant, and adds a 0.4B vision encoder — the 3B line does not list vision as a feature.

Ministral 3 8B 2512

3319°

#llm #mistralai #vision #agents #multilingual #local

Run this model

Offers / Ads

OpenRouter Terminal / API

Pay per token

Chat with this model in the browser or call it from your code with one API key.

Mistral | 262,144 token context | $0.15/M input, $0.15/M output. A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.

Guides for this model

Ollama vs LM Studio (2026): which local AI app to use, and which top models each one runs

Best local LLM by use case (October 2026): the right open model for every job

How much VRAM do I actually need for local AI?

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

Ministral 3 8B is Mistral's edge-optimised 8B instruct model with a vision encoder bolted on, released under Apache 2.0 so you can run it locally or deploy it commercially without asking permission. It fits in 12 GB of VRAM in FP8, supports a 262k-token context, and covers native function calling, JSON output and a solid spread of languages. If you need a capable small model that handles images and agents without a cloud bill, this is a reasonable place to start.

Known for

Runs locally in 12 GB VRAM (FP8); quantise further to go lower
262k-token context window in an 8B-class model
Native function calling and JSON output for agentic pipelines
Vision encoder handles image analysis alongside text
Apache 2.0: commercial use and modification allowed

Watch out for

FP8 weights ship by default; full-precision base is a separate download
Vision quality is from a 0.4B encoder — don't expect frontier-level image reasoning
Maker recommends temperature below 0.1 for production; higher settings need testing

Best for

Prompts to try

Agentic function-calling task

You have two tools: get_weather(city: str) and send_email(to: str, subject: str, body: str). A user says: 'Check the weather in Tokyo and email me at user@example.com with a short summary.' Plan the tool calls in order, show each call as a JSON object, then write the final email body.

Image description and extraction

Attach a photo of a receipt or invoice. List every line item, its quantity and price in a JSON array. Then write a one-sentence summary of the total spend and the vendor name. If any field is illegible, mark it as null rather than guessing.

Multilingual document summary

Here is a short news article in French: 'La Banque centrale européenne a maintenu ses taux directeurs inchangés lors de sa réunion de jeudi, citant une inflation stable et des perspectives économiques incertaines.' Summarise it in English, Spanish and Japanese, each in one sentence.

Compare with

Mistral Nemo
Open-weights model
131,072 token context · $0.03/M input, $0.03/M output
Mistral Large 4
API-only model
1,048,576 token context · $0.68/M input, $2.09/M output
Mistral Small 3.2 24B Instruct 2506
Open-weights model
128,000 token context · $0.07/M input, $0.20/M output
Ministral 3 3B 2512
Open-weights model
131,072 token context · $0.10/M input, $0.10/M output

More text models from mistralai

Questions people ask

Can I run Ministral 3 8B locally?: Yes — the weights are open under Apache 2.0 and available on Hugging Face. Mistral says it fits in 12 GB of VRAM in FP8, and less if you quantise further.
What does it cost via API, and how long is the context?: Pricing is $0.15 per million tokens for both input and output, with a 262,144-token context window.
How does the 8B differ from the 3B in the same family?: The 8B model has a larger 8.4B language model compared to the 3B variant, and adds a 0.4B vision encoder — the 3B line does not list vision as a feature.

Captain's verdict
A genuinely useful small model: open, cheap, vision-capable and agentic enough to justify the 12 GB ask.

Model card on Hugging Face

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.

Similar Models

AI Models for Image, Video & Text Generation

Ministral 3 8B 2512 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 multilingual local budget

Browse by Model Family