Hey there awesome participant!
I’m Oleg, the community manager on the Apertus team. We are a research group commited to advancing the state of the art of Large Language Models with some of the best hardware and smartest people around – and we are doing this as part of the Swiss AI Initiative (swiss-ai.org)
This document is aimed at the participants and organizers of hackathons in Switzerland, some of which we are supporting through our extended team and network of members and partners.
If you’ve never heard of it, no problem: we just had our first public release (affectionately known as 2509) a half year ago, as the post above will inform you. And already, there are several great ways to access Apertus! Let me tell you about how to get started with your hackathon projects:
Go local
Apertus is completely free (Apache 2.0 licensed) to download and use on your local or cloud machine. The 8B variant even runs very well on my run-of-the-mill Macbook! There are instructions for the adventurous –> Documentation including Ollama, LM Studio, vLLM and SGlang.
Screenshot of LM Studio from my blog post
New: visit our User Guides for other approaches to installing Apertus.
Think sovereign
You can get started with Apertus for free at Infomaniak using their AI Services page. They are a popular choice for many startups right now, with a climate-friendly new data centre in Geneva.
Public AI is a non-profit which runs hosting for select open models. Apertus inference is currently sponsored by CSCS - the same institution whose famous “Alps” supercomputer is being used to train Apertus! This is a demo service right now with relatively low rate limits, completely free for a limited time. It is quick and easy to get started with a personal API key at https://platform.publicai.co/docs
You can find further providers highlighted at –> Get Started
Act global
The Inference Endpoints of Swisscom’s Swiss AI Platform, as well as Hugging Face Inference Endpoints, were sponsored at hackathons during the launch of Apertus. They are both an excellent option for commercial users.
Featherless.ai launched the Open world campaign, and they are hosting both Apertus models on their platform. They have generously provided starter keys for our recent hackathons at the EPFL and ETHZ - just ping me if you need more access for your hack.
As a model compatible with open weight LLM standards, with community builds in GGUF, MLX and other formats, you should have no trouble running Apertus on the AI platforms of various commercial clouds. Tip: it is usually easier if they support loading models directly from Hugging Face.
You can find some recipes in the links in –> Get Started
Within academia
The Apertus team is contributing to the development of the Swiss AI Research Platform, and offers direct access to early versions of Apertus as well as other open-source models to our collaborators in the LLM development community.
The ETHZ HPC service has GPU clusters available. Renkulab is recommended for members of Swiss universities more widely.
For students and staff of the EPFL, we recommmend using the RCP AI as a Service platform. Select large language models are accessible through AI Inference As A Service at the Research Computing Platform of EPFL. The costs are generally covered by teaching or research grants. RCP is only accessible through the EPFL network, and provides an easy way to chat or connect via API to Apertus. The documentation can be found here.
Always be opening
So as you can see.. our schools, many companies, and even NGOs are invested into the idea of a truly sovereign and fully model as the foundation of great AI systems. But this vision depends on many of us making tough choices, and demanding fairness in AI.
Visit https://apertus-ai.org/subscribe to stay tuned.
More providers are on their way, and the list on our web page will be updated over time. Please drop us a line on the hackathon platform if you need help with this.
One more thing
We are hiring! (June 2026)
Hope you have a great time working with AI this weekend – can’t wait to see what you build or to hear of your learning experience. Drop me a mail or social media mention – keep it cool, keep it Open!