# EuroLLM-9B: Technical Report

arXiv: https://arxiv.org/abs/2506.04079 · HTML: https://mlsanity.com/paper/2506.04079/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Jun 2025.

## Built on by (most cited first, 17 of 17)

- [Parity-Aware Byte-Pair Encoding: Improving Cross-lingual Fairness in Tokenization](https://mlsanity.com/paper/2508.04796/) (2025)
- [Global PIQA: Evaluating Commonsense Reasoning Across 100+ Languages and Cultures](https://mlsanity.com/paper/2510.24081/) (2025)
- [Open-sci-ref-0.01: open and reproducible reference baselines for language model and dataset comparison](https://mlsanity.com/paper/2509.09009/) (2025)
- [Llama-GENBA-10B: A Trilingual Large Language Model for German, English and Bavarian](https://mlsanity.com/paper/2509.05668/) (2025)
- [BERT-as-a-Judge: A Robust Alternative to Lexical Methods for Efficient Reference-Based LLM Evaluation](https://mlsanity.com/paper/2604.09497/) (2026)
- [Building Large-Scale English-Romanian Literary Translation Resources with Open Models](https://mlsanity.com/paper/2509.07829/) (2025)
- [TowerVision: Understanding and Improving Multilinguality in Vision-Language Models](https://mlsanity.com/paper/2510.21849/) (2025)
- [CARTE: A Benchmark for Mapping Language Model Knowledge Across France](https://mlsanity.com/paper/2606.01995/) (2026)
- [A Sovereign, Open-Source Foundation Model for German and English](https://mlsanity.com/paper/2607.09424/) (2026)
- [Deriving Scaling Laws for OpenEuroLLM Models: Learning Rate, Batch Size and Loss](https://mlsanity.com/paper/2608.28308/) (2026)
- [Improving Term Evaluation in Machine Translation: Variation Matters](https://mlsanity.com/paper/2609.08779/) (2026)
- [Comparative Evaluation of Machine Translation Systems on Images with Text](https://mlsanity.com/paper/2605.29476/) (2026)
- [Trusting sovereign language models as scientific instruments: evidence from Portugal's AMALIA](https://mlsanity.com/paper/2607.08731/) (2026)
- [Lingua Franca or Probing Artifact? Rethinking Latent Language in Multilingual LLMs](https://mlsanity.com/paper/2609.00155/) (2026)
- [Which Models Work Well Together? Measuring Heterogeneity for LLM Team Selection](https://mlsanity.com/paper/2609.38274/) (2026)
- [Synthetic Pre-pretraining Survives Scale, but Not as a Grammatical Prior](https://mlsanity.com/paper/2609.39827/) (2026)
- [A theory of platonic representations in language models](https://mlsanity.com/paper/2610.07168/) (2026)

## Abstract (arXiv)

This report presents EuroLLM-9B, a large language model trained from scratch to support the needs of European citizens by covering all 24 official European Union languages and 11 additional languages. EuroLLM addresses the issue of European languages being underrepresented and underserved in existing open large language models. We provide a comprehensive overview of EuroLLM-9B's development, including tokenizer design, architectural specifications, data filtering, and training procedures. We describe the pre-training data collection and filtering pipeline, including the creation of EuroFilter, an AI-based multilingual filter, as well as the design of EuroBlocks-Synthetic, a novel synthetic dataset for post-training that enhances language coverage for European languages. Evaluation results demonstrate EuroLLM-9B's competitive performance on multilingual benchmarks and machine translation tasks, establishing it as the leading open European-made LLM of its size. To support open research and adoption, we release all major components of this work, including the base and instruction-tuned models, the EuroFilter classifier, and the synthetic post-training dataset.