EuroLLM1.5-SFT

⚠️ PREVIEW RELEASE: This is a preview version. The model is still under development and may have limitations in performance and stability. Use with caution in production environments.

Results

We compare EuroLLM1.5-9B-SFT against the previous EuroLLM releases (EuroLLM-9B-2512 and EuroLLM-22B-2512), the European open model Apertus-v1.5-8B, and two strong open-weight models of similar size, Qwen3.5-9B and Gemma 4 12B (both with thinking enabled), on English and multilingual benchmarks covering math, reasoning, coding, instruction following and knowledge.

Run the model

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "utter-project/EuroLLM1.5-9B-SFT"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, dtype="auto")

messages = [
    {
        "role": "system",
        "content": "You are EuroLLM --- an AI assistant specialized in European languages that provides safe, educational and helpful answers.",
    },
    {
        "role": "user", "content": "What is the capital of Portugal? How would you describe it?"
    },
    ]

inputs = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)
outputs = model.generate(**inputs, max_new_tokens=32768, do_sample=True, temperature=0.6, top_p=0.95)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Bias, Risks, and Limitations

EuroLLM1.5-9B has not been aligned to human preferences, so the model may generate problematic outputs (e.g., hallucinations, harmful content, or false statements).

Citation

If you use our work, please cite the following until the EuroLLM1.5 technical report is released:

@misc{ramos2026eurollm22btechnicalreport,
      title={EuroLLM-22B: Technical Report},
      author={Miguel Moura Ramos and Duarte M. Alves and Hippolyte Gisserot-Boukhlef and João Alves and Pedro Henrique Martins and Patrick Fernandes and José Pombal and Nuno M. Guerreiro and Ricardo Rei and Nicolas Boizard and Amin Farajian and Mateusz Klimaszewski and José G. C. de Souza and Barry Haddow and François Yvon and Pierre Colombo and Alexandra Birch and André F. T. Martins},
      year={2026},
      eprint={2602.05879},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2602.05879},
}