Instructions to use swiss-ai/Apertus-70B-Instruct-2509 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use swiss-ai/Apertus-70B-Instruct-2509 with Transformers:

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

pipe = pipeline("text-generation", model="swiss-ai/Apertus-70B-Instruct-2509")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("swiss-ai/Apertus-70B-Instruct-2509")
model = AutoModelForCausalLM.from_pretrained("swiss-ai/Apertus-70B-Instruct-2509", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use swiss-ai/Apertus-70B-Instruct-2509 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "swiss-ai/Apertus-70B-Instruct-2509"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "swiss-ai/Apertus-70B-Instruct-2509",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/swiss-ai/Apertus-70B-Instruct-2509

SGLang

How to use swiss-ai/Apertus-70B-Instruct-2509 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 "swiss-ai/Apertus-70B-Instruct-2509" \
    --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": "swiss-ai/Apertus-70B-Instruct-2509",
		"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 "swiss-ai/Apertus-70B-Instruct-2509" \
        --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": "swiss-ai/Apertus-70B-Instruct-2509",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use swiss-ai/Apertus-70B-Instruct-2509 with Docker Model Runner:
```
docker model run hf.co/swiss-ai/Apertus-70B-Instruct-2509
```

Support for AMD GPU

#12

by pawp81 - opened Nov 3, 2025

Discussion

pawp81

Nov 3, 2025

When trying to optimize the model for AMD GPU with Olive framework:
olive optimize --model_name swiss-ai/Apertus-70B-2509 --device gpu --provider VitisAIExecutionProvider

I get following error:
NotImplementedError: The swiss-ai/Apertus-70B-2509 model is not currently supported.

Here is my driver list:

loleg

Swiss AI Initiative org Apr 21

•

edited Apr 21

From the official docs I'm getting the impression that you are running this correctly, so it is indeed an incompatibility issue. I am aware of internal testing that has been successful with Sglang on the ROCm stack. If you can share any more specifics about your use case, or downstream libraries being used, that would help.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment