The AI landscape has been dominated by a handful of large language models, many of which operate as “black boxes” with hidden data and opaque training methods. But Apertus enters the AI space as the state-of-the-art model that is completely transparent, from its training data to its core architecture. Apertus, that comes in both 8B and 70B parameter variants, distinguishes itself not just with its size, but with its commitment to radical transparency and massive multilingualism. It was pre-trained on an unprecedented 15 trillion tokens, with over 40% of the data in languages other than English, providing native support for over 1,800 languages, a milestone that makes it uniquely valuable for global applications and under-resourced linguistic communities. Unlike many models that only offer their weights, Apertus provides all the scientific artifacts from its development cycle, including data preparation scripts, training code, and evaluation suites, allowing for transparent audits and community-driven extension. This model is a foundational blueprint for the future of ethical, compliant, and inclusive AI.
In this article, we’ll dive into the step-by-step installation, setup and usage process of this model.
Prerequisites
The minimum system requirements for running this model are:
- GPU: 1x RTX A6000 for 8B & 1xH200 or 2xH100 for 70B version
- Storage: 50 GB for 8B, 300 GB for 70B (preferable)
- VRAM: at least 16GB for 8B, 140GB for 70B
- Anaconda installed
Step-by-step process to install and run Apertus
For the purpose of this tutorial, we’ll use a GPU-powered Virtual Machine by NodeShift since it provides high compute Virtual Machines at a very affordable cost on a scale that meets GDPR, SOC2, and ISO27001 requirements. Also, it offers an intuitive and user-friendly interface, making it easier for beginners to get started with Cloud deployments. However, feel free to use any cloud provider of your choice and follow the same steps for the rest of the tutorial.
Step 1: Setting up a NodeShift Account
Visit app.nodeshift.com and create an account by filling in basic details, or continue signing up with your Google/GitHub account.
If you already have an account, login straight to your dashboard.
Step 2: Create a GPU Node
After accessing your account, you should see a dashboard (see image), now:
- Navigate to the menu on the left side.
- Click on the GPU Nodes option.
- Click on Start to start creating your very first GPU node.
These GPU nodes are GPU-powered virtual machines by NodeShift. These nodes are highly customizable and let you control different environmental configurations for GPUs ranging from H100s to A100s, CPUs, RAM, and storage, according to your needs.
Step 3: Selecting configuration for GPU (model, region, storage)
- For this tutorial, we’ll be using 1x RTX A6000 GPU, however, you can choose any GPU as per the prerequisites.
- Similarly, we’ll opt for 200GB storage by sliding the bar. You can also select the region where you want your GPU to reside from the available ones.
Step 4: Choose GPU Configuration and Authentication method
- After selecting your required configuration options, you’ll see the available GPU nodes in your region and according to (or very close to) your configuration. In our case, we’ll choose a 1x RTX A6000 48GB GPU node with 64vCPUs/63GB RAM/200GB SSD.
2. Next, you’ll need to select an authentication method. Two methods are available: Password and SSH Key. We recommend using SSH keys, as they are a more secure option. To create one, head over to our official documentation.
Step 5: Choose an Image
The final step is to choose an image for the VM, which in our case is Nvidia Cuda.
That’s it! You are now ready to deploy the node. Finalize the configuration summary, and if it looks good, click Create to deploy the node.
Step 6: Connect to active Compute Node using SSH
- As soon as you create the node, it will be deployed in a few seconds or a minute. Once deployed, you will see a status Running in green, meaning that our Compute node is ready to use!
- Once your GPU shows this status, navigate to the three dots on the right, click on Connect with SSH, and copy the SSH details that appear.
As you copy the details, follow the below steps to connect to the running GPU VM via SSH:
- Open your terminal, paste the SSH command, and run it.
2. In some cases, your terminal may take your consent before connecting. Enter ‘yes’.
3. A prompt will request a password. Type the SSH password, and you should be connected.
Output:
Next, If you want to check the GPU details, run the following command in the terminal:
!nvidia-smi
Step 7: Set up the project environment with dependencies
- Create a virtual environment using Anaconda.
conda create -n apertus python=3.11 -y && conda activate apertus
Output:
2. Install required dependencies.
pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu121
pip install einops timm pillow
pip install transformers==4.56.0
pip install git+https://github.com/huggingface/accelerate
pip install git+https://github.com/huggingface/diffusers
pip install huggingface_hub
pip install sentencepiece bitsandbytes protobuf decord numpy
Output:
3. Login to Hugging Face with HF READ token.
This is a gated model, make sure to get access granted from the model card.
hf auth login
Output:
4. Install and run jupyter notebook.
conda install -c conda-forge --override-channels notebook -y
conda install -c conda-forge --override-channels ipywidgets -y
jupyter notebook --allow-root
5. If you’re on a remote machine (e.g., NodeShift GPU), you’ll need to do SSH port forwarding in order to access the jupyter notebook session on your local browser.
Run the following command in your local terminal after replacing:
<YOUR_SERVER_PORT> with the PORT allotted to your remote server (For the NodeShift server – you can find it in the deployed GPU details on the dashboard).
<PATH_TO_SSH_KEY> with the path to the location where your SSH key is stored.
<YOUR_SERVER_IP> with the IP address of your remote server.
ssh -L 8888:localhost:8888 -p <YOUR_SERVER_PORT> -i <PATH_TO_SSH_KEY> root@<YOUR_SERVER_IP>
Output:
After this copy the URL you received in your remote server:
And paste this on your local browser to access the Jupyter Notebook session.
Step 8: Download and Run the model
- Open a Python notebook inside Jupyter.
2. Download the model checkpoints and run it for inference with a prompt of your choice.
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 model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
model_name,
).to(device)
# prepare the model input
prompt = """
You are a polyglot academic assistant. Read the information provided below and follow the instructions precisely.
1. **Read and Analyze (Italian):** Read the following paragraph about the Roman Empire and identify two key factors contributing to its decline.
> *"L'Impero Romano raggiunse la sua massima estensione nel II secolo d.C., ma iniziò a mostrare segni di declino nel III secolo. Le invasioni barbariche, la corruzione politica interna e le crisi economiche furono fattori determinanti. Le continue guerre di frontiera e le tensioni sociali misero a dura prova le risorse dell'impero, portando alla sua eventuale divisione."*
2. **Summarize and Translate (Spanish):** In Spanish, summarize the main points of the Italian paragraph you just read. Your summary should be no more than two sentences.
3. **Explain a Concept (Japanese):** In Japanese, explain the concept of **"imperial overstretch"** and how it relates to the Roman Empire's decline. Your explanation should be in a formal, academic tone.
4. **Create a List (Hindi):** Using the information from your Italian reading and Japanese explanation, create a list in Hindi of the three main reasons for the fall of the Roman Empire, including the term "imperial overstretch" (in English) as one of the points.
"""
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 output
generated_ids = model.generate(**model_inputs, max_new_tokens=32768)
# Get and decode the output
output_ids = generated_ids[0][len(model_inputs.input_ids[0]) :]
print(tokenizer.decode(output_ids, skip_special_tokens=True))
Output:
Conclusion
Apertus demonstrates how large language models can be powerful yet fully transparent, offering open weights, compliant training data, and support for over 1,800 languages, making it a game-changer for global and ethical AI adoption. By combining state-of-the-art performance with radical openness, it sets a new standard for inclusive multilingual models. And with NodeShift, you can seamlessly install, configure, and run Apertus in just a few steps, eliminating the usual complexity of deploying massive LLMs. This synergy of groundbreaking technology and streamlined infrastructure makes Apertus not only accessible to researchers and developers worldwide but also a practical tool to build the next wave of AI innovation.
