Pixtral 12B

Name: Pixtral 12B
Author: Mistral AI

Mistral AI · Providers EU

Catalogue only Open weights European provider

Sovereignty and hosting

Catalogue only

This model is catalogued for reference. It is not hosted on LLM EU yet, and no first-party endpoint serves it here. Requests to it go to the provider directly, under that provider's own terms.

Summary

Pixtral 12B is Mistral’s first vision-language model, released as open weights under Apache-2.0. Its configuration file declares a maximum position embedding of 131,072 tokens, and the card reports 52.5 on MMMU (chain of thought) and 90.7 on DocVQA. It has been superseded by later Mistral multimodal and Ministral releases but remains downloadable.

Specifications

Provider: Mistral AI (FR)
Context window: 131k
Parameters: 12B
Modalities: text, vision
License: apache-2.0 · licence
Open weights: yes
Release date: 11 Sept 2024
Tasks: vision, rag, summarization

Languages

Strong: en

Adequate: fr, de, es, it, pt

Languages

Strong

Adequate

Not verified: the provider has not documented this claim. — a language is listed as strong only where a source claims it; the card links the evidence where one exists.

When to use it

Strengths

open-weight document and image understanding
128k-token context for multi-page inputs
Apache-2.0 licence

Limits

superseded by newer Mistral multimodal releases
scores are self-reported and date from September 2024
no evaluation has been run by LLM EU

Pricing

This model is catalogued for reference. It is not hosted on LLM EU yet, and no first-party endpoint serves it here. Requests to it go to the provider directly, under that provider's own terms.

Verification status

Where a field has no source, the card shows it as unverified instead of filling it in. An empty field is information.

LLM EU Verified means documented, not legally certified. It is not an AI Act conformity assessment and LLM EU is not an EU body.

Versions and variants

catalogue · Catalogue only · weights

Example request

curl https://api.llmeu.com/v1/chat/completions \
  -H "Authorization: Bearer $LLMEU_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"pixtral-12b","messages":[{"role":"user","content":"Hello"}]}'

No playground is deployed for this model: no endpoint serves it, so a request would have nowhere to go.

Benchmarks

MMMU (CoT): 52.5 (vendor-reported) source
DocVQA (ANLS): 90.7 (vendor-reported) source
MMLU (5-shot): 69.2 (vendor-reported) source

Sources

huggingface.co

Card changelog

11 Sept 2024 — Release date
19 Sept 2026 — Last reviewed

Last reviewed: 19 Sept 2026

Tasks

Vision