GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
apertus-ai
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
apertus-ai
Model Tree
Input Modalities
Output Modalities
Supported Functionality
Apertus is a 70B and 8B parameter language model designed to push the boundaries of fully-open multilingual and transparent models. The model supports over 1000 languages and long context, it uses only fully compliant and open training data, and achieves comparable performance to models trained behind closed doors.
The model is a decoder-only transformer, pretrained on 15T tokens with a staged curriculum of web, code and math data. The model uses a new xIELU activation function and is trained from scratch with the AdEMAMix optimizer. Post-training included supervised fine-tuning and alignment via QRPO.
For more details refer to our technical report
Apertus 1.5, our latest model release, builds on the strengths of previous versions by focusing on three key areas:
We are working with inference providers to ensure global availability on multiple platforms at launch. These will be linked in our Get Started page
The modeling code for Apertus is available in Transformers v4.56.0 and later, so make sure to upgrade your version. You can also load the model with the latest vLLM which uses Transformers as a backend.
bash
pip install -U transformerspython
from transformers import AutoModelForCausalLM, AutoTokenizer model_name = "swiss-ai/Apertus-8B-Instruct-2509"device = "cuda" # for GPU usage or "cpu" for CPU usage # load the tokenizer and the modeltokenizer = AutoTokenizer.from_pretrained(model_name)model = AutoModelForCausalLM.from_pretrained( model_name,).to(device) # prepare the model inputprompt = "Give me a brief explanation of gravity in simple terms."messages_think = [ {"role": "user", "content": prompt}] text = tokenizer.apply_chat_template( messages_think, tokenize=False, add_generation_prompt=True,)model_inputs = tokenizer([text], return_tensors="pt", add_special_tokens=False).to(model.device) # Generate the outputgenerated_ids = model.generate(**model_inputs, max_new_tokens=32768) # Get and decode the outputoutput_ids = generated_ids[0][len(model_inputs.input_ids[0]) :]print(tokenizer.decode(output_ids, skip_special_tokens=True))[!TIP] We recommend setting
temperature=0.8andtop_p=0.9in the sampling parameters.
Apertus by default supports a context length up to 262'144 tokens.
Apertus supports tool use with newer versions of the chat template, such as the version shipped with vLLM 0.22.0 and above.
Deployment of the models is directly supported by the newest versions of Transformers, vLLM, SGLang, and also for running on-device with MLX or GGUF as loading formats.
There is a diverse community creating quantized and reformatted versions of the Apertus models. We will endeavor to support the main formats with an official build on our Hugging Face organization. A few outstanding community versions are linked from our documentation. Use 3rd party builds at your own risk, and contact us for a quick validation before going to production.
Benchmark evaluations, for pretraining and posttraining phases, multilingual evaluations in around hundred languages, and long context evaluations are provided in Section 5 of the Apertus Tech Report
All elements used in the training process are made openly available
Apertus can produce text on a variety of topics, but the generated content may not always be factually accurate, logically consistent, or free from biases present in the training data. These models should be used as assistive tools rather than definitive sources of information. Users should always verify important information and critically evaluate any generated content.
These are being updated for Apertus 1.5. For documentation of the initial release, see:
For removal requests of personally identifiable information (PII) or of copyrighted content, please contact the respective dataset owners or us directly
To contact us, please use the links at https://apertvs.ai/contact/ or send an email to llm-requests@swiss-ai.org
bash
@misc{swissai2025apertus, title={{Apertus: Democratizing Open and Compliant LLMs for Global Language Environments}}, author={Alejandro Hernández-Cano and Alexander Hägele and Allen Hao Huang and Angelika Romanou and Antoni-Joan Solergibert and Barna Pasztor and Bettina Messmer and Dhia Garbaya and Eduard Frank Ďurech and Ido Hakimi and Juan García Giraldo and Mete Ismayilzada and Negar Foroutan and Skander Moalla and Tiancheng Chen and Vinko Sabolčec and Yixuan Xu and Michael Aerni and Badr AlKhamissi and Ines Altemir Marinas and Mohammad Hossein Amani and Matin Ansaripour and Ilia Badanin and Harold Benoit and Emanuela Boros and Nicholas Browning and Fabian Bösch and Maximilian Böther and Niklas Canova and Camille Challier and Clement Charmillot and Jonathan Coles and Jan Deriu and Arnout Devos and Lukas Drescher and Daniil Dzenhaliou and Maud Ehrmann and Dongyang Fan and Simin Fan and Silin Gao and Miguel Gila and María Grandury and Diba Hashemi and Alexander Hoyle and Jiaming Jiang and Mark Klein and Andrei Kucharavy and Anastasiia Kucherenko and Frederike Lübeck and Roman Machacek and Theofilos Manitaras and Andreas Marfurt and Kyle Matoba and Simon Matrenok and Henrique Mendoncça and Fawzi Roberto Mohamed and Syrielle Montariol and Luca Mouchel and Sven Najem-Meyer and Jingwei Ni and Gennaro Oliva and Matteo Pagliardini and Elia Palme and Andrei Panferov and Léo Paoletti and Marco Passerini and Ivan Pavlov and Auguste Poiroux and Kaustubh Ponkshe and Nathan Ranchin and Javi Rando and Mathieu Sauser and Jakhongir Saydaliev and Muhammad Ali Sayfiddinov and Marian Schneider and Stefano Schuppli and Marco Scialanga and Andrei Semenov and Kumar Shridhar and Raghav Singhal and Anna Sotnikova and Alexander Sternfeld and Ayush Kumar Tarun and Paul Teiletche and Jannis Vamvas and Xiaozhe Yao and Hao Zhao Alexander Ilic and Ana Klimovic and Andreas Krause and Caglar Gulcehre and David Rosenthal and Elliott Ash and Florian Tramèr and Joost VandeVondele and Livio Veraldi and Martin Rajman and Thomas Schulthess and Torsten Hoefler and Antoine Bosselut and Martin Jaggi and Imanol Schlag}, year={2025}, howpublished={\url{https://arxiv.org/abs/2509.14233}}}from transformers import AutoModelForCausalLM, AutoTokenizer model_name = "swiss-ai/Apertus-8B-Instruct-2509"device = "cuda" # for GPU usage or "cpu" for CPU usage # load the tokenizer and the modeltokenizer = AutoTokenizer.from_pretrained(model_name)model = AutoModelForCausalLM.from_pretrained( model_name,).to(device) # prepare the model inputprompt = "Give me a brief explanation of gravity in simple terms."messages_think = [ {"role": "user", "content": prompt}] text = tokenizer.apply_chat_template( messages_think, tokenize=False, add_generation_prompt=True,)model_inputs = tokenizer([text], return_tensors="pt", add_special_tokens=False).to(model.device) # Generate the outputgenerated_ids = model.generate(**model_inputs, max_new_tokens=32768) # Get and decode the outputoutput_ids = generated_ids[0][len(model_inputs.input_ids[0]) :]print(tokenizer.decode(output_ids, skip_special_tokens=True))@misc{swissai2025apertus, title={{Apertus: Democratizing Open and Compliant LLMs for Global Language Environments}}, author={Alejandro Hernández-Cano and Alexander Hägele and Allen Hao Huang and Angelika Romanou and Antoni-Joan Solergibert and Barna Pasztor and Bettina Messmer and Dhia Garbaya and Eduard Frank Ďurech and Ido Hakimi and Juan García Giraldo and Mete Ismayilzada and Negar Foroutan and Skander Moalla and Tiancheng Chen and Vinko Sabolčec and Yixuan Xu and Michael Aerni and Badr AlKhamissi and Ines Altemir Marinas and Mohammad Hossein Amani and Matin Ansaripour and Ilia Badanin and Harold Benoit and Emanuela Boros and Nicholas Browning and Fabian Bösch and Maximilian Böther and Niklas Canova and Camille Challier and Clement Charmillot and Jonathan Coles and Jan Deriu and Arnout Devos and Lukas Drescher and Daniil Dzenhaliou and Maud Ehrmann and Dongyang Fan and Simin Fan and Silin Gao and Miguel Gila and María Grandury and Diba Hashemi and Alexander Hoyle and Jiaming Jiang and Mark Klein and Andrei Kucharavy and Anastasiia Kucherenko and Frederike Lübeck and Roman Machacek and Theofilos Manitaras and Andreas Marfurt and Kyle Matoba and Simon Matrenok and Henrique Mendoncça and Fawzi Roberto Mohamed and Syrielle Montariol and Luca Mouchel and Sven Najem-Meyer and Jingwei Ni and Gennaro Oliva and Matteo Pagliardini and Elia Palme and Andrei Panferov and Léo Paoletti and Marco Passerini and Ivan Pavlov and Auguste Poiroux and Kaustubh Ponkshe and Nathan Ranchin and Javi Rando and Mathieu Sauser and Jakhongir Saydaliev and Muhammad Ali Sayfiddinov and Marian Schneider and Stefano Schuppli and Marco Scialanga and Andrei Semenov and Kumar Shridhar and Raghav Singhal and Anna Sotnikova and Alexander Sternfeld and Ayush Kumar Tarun and Paul Teiletche and Jannis Vamvas and Xiaozhe Yao and Hao Zhao Alexander Ilic and Ana Klimovic and Andreas Krause and Caglar Gulcehre and David Rosenthal and Elliott Ash and Florian Tramèr and Joost VandeVondele and Livio Veraldi and Martin Rajman and Thomas Schulthess and Torsten Hoefler and Antoine Bosselut and Martin Jaggi and Imanol Schlag}, year={2025}, howpublished={\url{https://arxiv.org/abs/2509.14233}}}