Skip to content

Mistral AI · Chat

Ministral 3 3B

Mistral AI 🇫🇷Chat
From Eurouter's listing:
Ministral 3 3B is an open Mistral AI model for efficient text and vision workloads.
llminfo IQ
≈ 94
Maker's price
$0.10 blended / 1M
Max context
262K
Listings
2

Evidence and sources

llminfo IQ ≈ 94, ranked among chat models. From 32 benchmarks. Little data behind it, so treat it as a rough estimate.How llminfo IQ is computedReleased 2 Dec 2025Maker HQ: FR (according to Mistral AI's own website)
Sources: LiteLLM data, EURouter data, llminfo researchPrimary data from LiteLLM from EURouter: name, description from llminfo research: release date
Tags from its sources:open-sourcevisionlightweightlong-context

Advantages and trade-offs

Compared with 10 chat models, picked mainly by popularity and IQ
We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 06:07 UTC.Prices come from the model's maker where they sell it, otherwise their official partner, otherwise the market median. This comparison uses 7 maker's prices; 2 market median prices.

Input & output

as stated by the model's providers
Text
Images
Files
Text

Capabilities

Supported operations and provider-stated features

VisionFunction callingStructured output

Listings

 Mistral AImistral/ministral-3-3b-2512 · 2512Source: LiteLLM data131K$0.10cache read $0.01$0.10
 Eurouterministral-3-3bSource: EURouter data262K$0.11cache read $0.011$0.11

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

Factuality

Data credits: Vectara Hallucination Leaderboard, Apache-2.0 (licence)

Around the web

  • Ministral 8B - Mistral AI | Mistral Docs
    Docs & API Search docs ⌘K Getting Started Models Products Developers Admin API Search docs …Docs & API Search docs ⌘K Getting Started Models Products Developers Admin API Search docs ⌘K Toggle theme Reach out Try Studio 1. 3. Models 5. Model Cards 7. Ministral 8B Try in playground ↗ Ministr…

    docs.mistral.ai

  • mistralai / ministral-14b-instruct-2512
    Ministral 3 Family on Hugging Face Ministral 3 14B Instruct BF16 Version vLLM Framework Mistral …Ministral 3 Family on Hugging Face Ministral 3 14B Instruct BF16 Version vLLM Framework Mistral Common Library System Prompt Configuration Ministral 3 Family Model Name · Type · Precision · Link Mini…

    docs.api.nvidia.com

  • Ministral 3 - a mistralai Collection - Hugging Face
    mistralai 's Collections Mistral Medium 3.5 Voxtral Mistral Small 4 Devstral 2 Mistral Large 3 …mistralai 's Collections Mistral Medium 3.5 Voxtral Mistral Small 4 Devstral 2 Mistral Large 3 Ministral 3 Ministral 3 - Additional Checkpoints Speech Evals Ministral 3 updated Dec 2, 2025 A collecti…

    huggingface.co

  • mistralai/Ministral-3-8B-Instruct-2512-BF16 · Hugging Face
    Key Features Ministral 3 8B consists of two main architectural components: Model Name · Type …Key Features Ministral 3 8B consists of two main architectural components: Model Name · Type · Precision · Link Ministral 3 3B Base 2512 · Base pre-trained · BF16 · Hugging Face Ministral 3 3B Instru…

    huggingface.co

  • mistralai/Ministral-3-3B-Instruct-2512-BF16 · Hugging Face
    Instruct-2512-BF16 like 32 Follow Mistral AI_ 18.2k Safetensors 11 languages vllm mistral3 mistral-common arxiv: 2601.08584 …Instruct-2512-BF16 like 32 Follow Mistral AI_ 18.2k Safetensors 11 languages vllm mistral3 mistral-common arxiv: 2601.08584 License: apache-2.0 Model card Files Files and versions xet Community 2 Cop…

    web.archive.org

  • mistralai/Ministral-8B-Instruct-2410 · Hugging Face
    We introduce two new state-of-the-art models for local intelligence, on-device computing, and at-the-edge use cases. …We introduce two new state-of-the-art models for local intelligence, on-device computing, and at-the-edge use cases. We call them les Ministraux: Ministral 3B and Ministral 8B. The Ministral-8B-Instr…

    huggingface.co

  • README.md · mistralai/Ministral-3-14B-Base-2512 at main
    The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and …The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and efficient language…

    huggingface.co

  • Ministral 3 — Megatron Bridge - NVIDIA Documentation Hub

    Ministral 3 8B Base: https://huggingface.co/mistralai/Ministral-3-8B-Base-2512 Ministral 3 8B Instruct: https://huggingface.co/mistralai/Ministral-3-8B-Instruct-2512 Ministral 3 14B Base: https://hug…

    docs.nvidia.com

  • mistralai/Ministral-3-14B-Reasoning-2512 at f58588402aac1343ab2897a963b2297de9b5a516
    mistralai / Ministral-3-14B-Reasoning-2512 like 146 Follow Mistral AI_ 18.9k Safetensors 11 languages vllm mistral3 mistral-common …mistralai / Ministral-3-14B-Reasoning-2512 like 146 Follow Mistral AI_ 18.9k Safetensors 11 languages vllm mistral3 mistral-common arxiv: 2601.08584 License: apache-2.0 Model card Files Files and ver…

    huggingface.co

  • mistralai/Ministral-3-14B-Base-2512 at a813605c078903c4d9869fcc1792823a22106eb3
    mistralai / Ministral-3-14B-Base-2512 like 60 Follow Mistral AI_ 18.9k Safetensors 11 languages vllm mistral3 mistral-common …mistralai / Ministral-3-14B-Base-2512 like 60 Follow Mistral AI_ 18.9k Safetensors 11 languages vllm mistral3 mistral-common arxiv: 2601.08584 License: apache-2.0 Model card Files Files and versions …

    huggingface.co

Also known as: mistral/ministral-3-3b-2512

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works