Mistral NeMo 12B Instruct

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

Mistral NeMo is a 12B model built with NVIDIA, released under Apache-2.0 with a 128k-token context window and a Tekken tokenizer. The card reports 68.0% on 5-shot MMLU and lists English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese and Russian as supported languages. It remains a common choice where a permissive licence and a small footprint matter more than peak quality.

Specifications

Provider
Mistral AI (FR)
Context window
131k
Parameters
12.25B
Modalities
text
License
apache-2.0 · licence
Open weights
yes
Release date
17 Jul 2024
Tasks
cheap, multilingual-support, summarization, rag

Languages

Strong: en, fr, de, es, it, pt

Adequate: zh, ja, ru

Languages

Strong

  • en
  • fr
  • de
  • es
  • it
  • pt

Adequate

  • zh
  • ja
  • ru

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

  • 128k-token context window in the 12B class
  • Apache-2.0 licence with no user threshold
  • nine declared languages including the large EU ones
  • small enough for a single mid-range accelerator

Limits

  • quality is below current 12B to 30B releases
  • released July 2024 and not updated since
  • no evaluation has been run by LLM EU