Instructions to use utter-project/EuroLLM1.5-9B-SFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use utter-project/EuroLLM1.5-9B-SFT with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="utter-project/EuroLLM1.5-9B-SFT")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("utter-project/EuroLLM1.5-9B-SFT")
model = AutoModelForCausalLM.from_pretrained("utter-project/EuroLLM1.5-9B-SFT", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use utter-project/EuroLLM1.5-9B-SFT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "utter-project/EuroLLM1.5-9B-SFT"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "utter-project/EuroLLM1.5-9B-SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/utter-project/EuroLLM1.5-9B-SFT

SGLang

How to use utter-project/EuroLLM1.5-9B-SFT with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "utter-project/EuroLLM1.5-9B-SFT" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "utter-project/EuroLLM1.5-9B-SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "utter-project/EuroLLM1.5-9B-SFT" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "utter-project/EuroLLM1.5-9B-SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use utter-project/EuroLLM1.5-9B-SFT with Docker Model Runner:
```
docker model run hf.co/utter-project/EuroLLM1.5-9B-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.

	EuroLLM1.5-9B-SFT	EuroLLM-9B-2512	EuroLLM-22B-2512	Apertus-v1.5-8B	Qwen3.5-9B	Gemma 4 12B
English
Math
GSM8K	94.6	75.6	85.1	91.6	96.6	96.5
MATH-500	94.6	36.0	53.4	84.6	97.0	99.4
Reasoning
ARC-C	93.3	85.1	88.8	89.6	97.0	97.9
BBH	78.0	44.4	55.5	71.6	90.6	91.7
Coding
HumanEval	84.1	40.2	54.9	65.2	89.6	96.3
MBPP	84.3	53.5	57.0	67.4	89.3	95.8
Instruction Following
IFEval	75.8	68.2	74.5	84.8	89.3	93.9
Knowledge
MMLU	77.0	63.7	69.6	71.3	88.5	86.7
Multilingual
Math
MGSM	83.9	70.0	76.5	83.7	91.2	91.4
Reasoning
M-ARC	89.1	73.6	79.9	87.3	94.9	95.8
mLogiQA	53.6	36.7	41.6	44.5	76.7	77.2
Knowledge
Global-MMLU	72.9	58.1	63.7	71.3	84.7	84.1

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}, 
}

Downloads last month: 33

Safetensors

Model size

9B params

Tensor type

BF16

Paper for utter-project/EuroLLM1.5-9B-SFT

EuroLLM-22B: Technical Report

Paper • 2602.05879 • Published Feb 5 • 4