EuroLLM-1.7B-Instruct

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-1.7B-Instruct is the smallest model of the EuroLLM family, trained on 4 trillion tokens across the same 35 languages as the larger sizes. It is Apache-2.0 licensed and its configuration allows a 4096-token context. It is intended for translation and lightweight multilingual tasks on small hardware, not for reasoning-heavy work.

Specifications

Provider
EuroLLM (utter-project) (PT)
Context window
4.1k
Parameters
1.66B
Modalities
text
License
apache-2.0 · licence
Open weights
yes
Release date
06 Aug 2024
Tasks
cheap, translation, multilingual-support

Languages

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

Adequate: pl, nl, sv, cs, el, ro, fi, da, uk, 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

Adequate

  • pl
  • nl
  • sv
  • cs
  • el
  • ro
  • fi
  • da
  • uk
  • 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

  • runs on CPU-class or very small GPU hardware
  • 35 declared languages including all EU official languages
  • Apache-2.0 licence

Limits

  • 4096-token context window
  • limited reasoning and instruction-following capacity at 1.7B parameters
  • no evaluation has been run by LLM EU