Ministral 3 3B
Language modelOpen weightsCard summarizedMinistral 3 3B is the smallest and most efficient model in the Ministral 3 family, offering robust language and vision capabilities in a compact package.
Active (GA, v25.12)● Re-checked 12 Oct 2026 · 38 facts · 0 corrections · 1 unconfirmedSource: Ministral 3 3B Instruct 2512 model card (Hugging Face) and Introducing Mistral 3 launch post
Use it via API
Where to call it
- Mistral API (Mistral AI Studio)
ministral-3b-2512 - Self-host (weights)
mistralai/Ministral-3-3B-Instruct-2512
Good for
- Image captioning
- Text classification
- Real-time translation
Overview
Ministral 3 3B
Ministral 3 3B is the smallest and most efficient model in the Ministral 3 family, offering robust language and vision capabilities in a compact package.
- Cost
- $0.10 in
- Context
- 256K
- Input / output
- $0.10 / $0.10
- Max output
- —
- Knows up to
- —
- Released
- 2 Dec 2025
The smallest Ministral 3 model, a small language model with vision. It pairs a 3.4B language model with a 0.4B vision encoder, has a 256K context window and is released under Apache 2.0 in Base, Instruct (FP8) and Reasoning variants. Mistral says the FP8 Instruct weights fit in 8GB of VRAM. model card intro; Key Features
ministral-3b-2512- Input / output per 1M
- $0.10 / $0.10
- Context window
- 256K
- Max output
- —
- Knows up to
- —
- Reasoning
- —
- Weights
- Open · Apache 2.0
About this card. A model card is the maker's own account of a model: what it's for, how it was trained and tested, and where it falls short. This page condenses Mistral AI's Ministral 3 3B Instruct 2512 model card (Hugging Face) and Introducing Mistral 3 launch post. Every claim carries its source page.