Skip to main content
Watch: I Built an AI App Without Leaving Databricks

Mistral AI - Dense - verified

Run Ministral 3 3B Instruct 2512 locally

Ministral 3 3B Instruct 2512 is a 3.8B dense model from Mistral AI with a 262K-token context window, released under Apache 2.0 (commercial use is allowed); the smallest listed download is 2.1 GB, the Q4_K_M GGUF build from mistralai/Ministral-3-3B-Instruct-2512-GGUF.

Official weights: mistralai/Ministral-3-3B-Instruct-2512 - modalities: text, image

Total params
3.8B
Architecture
Dense
Context
262K
Smallest download
2.1 GB

Fits in

Smallest download at most 85% of memory

Downloads

The official weights and every quantization listed for this model, with file sizes from Hugging Face.

Ministral 3 3B Instruct 2512 downloads and file sizes
DownloadFormatSizeRepo
Official weightsFP84.7 GBmistralai/Ministral-3-3B-Instruct-2512
Q4_K_MSmallest listedGGUF2.1 GBmistralai/Ministral-3-3B-Instruct-2512-GGUF
Q8_0GGUF3.7 GBmistralai/Ministral-3-3B-Instruct-2512-GGUF
4bitMLX2.7 GBmlx-community/Ministral-3-3B-Instruct-2512-4bit

GB is decimal: 1 GB = 10^9 bytes. Add memory for the context and the operating system on top of the file size.

Run it

Copied verbatim from the page linked under each command. Server commands from model cards often assume a multi-GPU node; check the flags before you run them.

Ollama

Terminal
ollama run ministral-3:3b

Source: ollama.com/library/ministral-3:3b

vLLM

Terminal
vllm serve mistralai/Ministral-3-3B-Instruct-2512 \
  --tokenizer_mode mistral --config_format mistral --load_format mistral \
  --enable-auto-tool-choice --tool-call-parser mistral

Source: huggingface.co/mistralai/Ministral-3-3B-Instruct-2512

Not sure which runtime to use? Compare local LLM runtimes by platform, API and features.

License

License
Apache 2.0apache-2.0
Commercial use
Commercial use: YesCommercial use is allowed.
Gated download
No. The files download directly.

Worth knowing

The Ollama library page says this model requires Ollama 0.13.1 or later, and the weights pair a 3.4B language model with a 0.4B vision encoder.

Released (per the announcement).

API pricing and specsHosted prices per 1M tokens for Ministral 3 3B Instruct 2512, if you would rather not run it yourself.

FAQ

How big is the Ministral 3 3B Instruct 2512 download?

The official FP8 weights in mistralai/Ministral-3-3B-Instruct-2512 are 4.7 GB. The smallest listed download is 2.1 GB, the Q4_K_M GGUF build from mistralai/Ministral-3-3B-Instruct-2512-GGUF. Plan for more memory than the file size: the context (KV cache) and the operating system need room too.

Can I use Ministral 3 3B Instruct 2512 commercially?

Ministral 3 3B Instruct 2512 is released under Apache 2.0, and commercial use is allowed. The license text is at https://www.apache.org/licenses/LICENSE-2.0.

How much memory do I need for Ministral 3 3B Instruct 2512?

By this directory's rule of thumb it fits in 8 GB and up: the smallest listed download, 2.1 GB, is at most 85% of 8 GB, which leaves room for the context and the operating system.

How do I run Ministral 3 3B Instruct 2512 with Ollama?

Run "ollama run ministral-3:3b", as shown at https://ollama.com/library/ministral-3:3b. The Ollama library lists the ministral-3:3b tag at 3.0GB.

What is the context length of Ministral 3 3B Instruct 2512?

262,144 tokens. A longer context needs more memory for the KV cache, so you can run with a shorter one when memory is tight.

Sources

Last verified from the pages below.

Newsletter

New open weights, every week

One email per week. New model releases, open-weight drops and what they mean for what you build.

Keep exploring

Best local AI models

Our curated picks by hardware tier, with benchmarks and the reasoning.

Model API pricing and specs

First-party prices per 1M tokens when you would rather call an API.

AI benchmark leaderboards

Sourced scores, for when you need to compare quality.

Setup guides

Point your coding tools at the model you picked.