GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
utter-project
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
utter-project
Model Tree
Input Modalities
Output Modalities
Supported Functionality
The EuroLLM project has the goal of creating a suite of LLMs capable of understanding and generating text in all European Union languages as well as some additional relevant languages. EuroLLM-22B is a 22B parameter model trained on 4 trillion tokens divided across the considered languages and several data sources: Web data, parallel data (en-xx and xx-en), and high-quality datasets. EuroLLM-22B-Instruct was further instruction tuned on EuroBlocks, an instruction tuning dataset with focus on general instruction-following and machine translation.
EuroLLM uses a standard, dense Transformer architecture withgrouped query attention (GQA), pre-layer normalization with RMSNorm, SwiGLU activations and rotary positional embeddings (RoPE) in every layer. Here is a summary of the model hyper-parameters:
| Sequence Length | 32,768 |
| Number of Layers | 56 |
| Embedding Size | 6,144 |
| FFN Hidden Size | 16,384 |
| Number of Heads | 48 |
| Number of KV Heads (GQA) | 8 |
| Activation Function | SwiGLU |
| Position Encodings | RoPE (\Theta=1,000,000) |
| Layer Norm | RMSNorm |
| Tied Embeddings | No |
| Embedding Parameters | 0.786B |
| LM Head Parameters | 0.786B |
| Non-embedding Parameters | 21.067B |
| Total Parameters | 22.639B |
EuroLLM-22B was trained on approximately 4 trillion tokens, using 400 Nvidia H100 GPUs on the MareNostrum5 supercomputer, thanks to an EuroHPC extreme-scale access grant. The training process was carefully structured into three key phases:
This model was not post-trained. For an instruction-following version of this model see EuroLLM-22B-Instruct-2515.
markdown
from transformers import AutoModelForCausalLM, AutoTokenizermodel_id = "utter-project/EuroLLM-22B-2512"tokenizer = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained(model_id)text = "English: My name is EuroLLM. Portuguese:"inputs = tokenizer(text, return_tensors="pt")outputs = model.generate(**inputs, max_new_tokens=20)print(tokenizer.decode(outputs[0], skip_special_tokens=True))
EuroLLM-22B has not been aligned to human preferences, so the model may generate problematic outputs (e.g., hallucinations, harmful content, or false statements).
If you use our work, please cite:
markdown
@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},}