Evidence-backed European AI register
EuroLLM-22B / EuroLLM-22B-Instruct-2512
Organisation-scoped listings, specifications and token pricing; origin and hosting are not inferred.
Dataset compiled 2026-08-27 · evidence over inference
Interpretation
This is a neutral availability profile assembled from organisation-scoped listings and exact public price labels. It does not assert that the model is European, identify its creator, prove current service availability without a current price offer, or establish hosting and runtime geography.
Organisation-scoped listings
- EuroLLM
catalogued model listing
- Type
- text
- Parameters
- 22.64B total (21.07B non-embedding), dense transformer, GQA, RMSNorm pre-LN, SwiGLU, RoPE
- Context
- 32,768 tokens
- Languages
- 35 languages: all 24 official EU languages plus Arabic, Catalan, Chinese, Galician, Hindi, Japanese, Korean, Norwegian, Russian, Turkish, Ukrainian (11 additional strategic languages)
- Licence
- Apache-2.0
- Release
- 2026-02