EuroLLM-22B-Instruct (2512)

EuroLLM (utter-project) · Providers EU

Not hosted — mock backend Open weights European provider

Sovereignty and hosting

Not hosted — mock backend

Not hosted on LLM EU on this deployment: requests are answered by the built-in mock backend in region dev-mock. No weights run.

Summary

EuroLLM-22B-Instruct (2512) is the largest released EuroLLM model, covering the same European language set as the 9B version. The model card states that long-context data sources were upsampled in training to extend the context window to 32k tokens. It is published under Apache-2.0 and is the reference checkpoint for the project’s post-training recipe.

Specifications

Provider
EuroLLM (utter-project) (PT)
Context window
33k
Parameters
22.64B
Modalities
text
License
apache-2.0 · licence
Open weights
yes
Release date
05 Dec 2025
Tasks
translation, multilingual-support, summarization, reasoning

Languages

Strong: en, de, es, fr, it, pt, pl, nl, sv, cs, el, ro, fi, da, uk

Adequate: hu, bg, sk, sl, lt, lv, et, hr, ga, mt, ca, tr, ar, zh, ja, ko, ru, hi

Languages

Strong

  • en
  • de
  • es
  • fr
  • it
  • pt
  • pl
  • nl
  • sv
  • cs
  • el
  • ro
  • fi
  • da
  • uk

Adequate

  • hu
  • bg
  • sk
  • sl
  • lt
  • lv
  • et
  • hr
  • ga
  • mt
  • ca
  • tr
  • ar
  • zh
  • ja
  • ko
  • ru
  • hi

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

  • largest openly licensed model trained specifically for EU languages
  • Apache-2.0 licence
  • reference checkpoint for the project post-training recipe

Limits

  • no benchmark table is published on the model card
  • 32k-token context window
  • no evaluation has been run by LLM EU