Instructions to use ArtusDev/swiss-ai_Apertus-70B-Instruct-2509-EXL3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ArtusDev/swiss-ai_Apertus-70B-Instruct-2509-EXL3 with Transformers:

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

pipe = pipeline("text-generation", model="ArtusDev/swiss-ai_Apertus-70B-Instruct-2509-EXL3")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("ArtusDev/swiss-ai_Apertus-70B-Instruct-2509-EXL3", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ArtusDev/swiss-ai_Apertus-70B-Instruct-2509-EXL3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ArtusDev/swiss-ai_Apertus-70B-Instruct-2509-EXL3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ArtusDev/swiss-ai_Apertus-70B-Instruct-2509-EXL3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ArtusDev/swiss-ai_Apertus-70B-Instruct-2509-EXL3

SGLang

How to use ArtusDev/swiss-ai_Apertus-70B-Instruct-2509-EXL3 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 "ArtusDev/swiss-ai_Apertus-70B-Instruct-2509-EXL3" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ArtusDev/swiss-ai_Apertus-70B-Instruct-2509-EXL3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "ArtusDev/swiss-ai_Apertus-70B-Instruct-2509-EXL3" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ArtusDev/swiss-ai_Apertus-70B-Instruct-2509-EXL3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ArtusDev/swiss-ai_Apertus-70B-Instruct-2509-EXL3 with Docker Model Runner:
```
docker model run hf.co/ArtusDev/swiss-ai_Apertus-70B-Instruct-2509-EXL3
```

ArtusDev/swiss-ai_Apertus-70B-Instruct-2509-EXL3

EXL3 quants of swiss-ai/Apertus-70B-Instruct-2509 using exllamav3 for quantization.

Quants

Quant	BPW	Head Bits
2.5_H6	2.5	6
3.0_H6	3.0	6
3.5_H6	3.5	6
4.0_H6	4.0	6
4.25_H6	4.25	6
5.0_H6	5.0	6
6.0_H6	6.0	6
8.0_H8	8.0	8

How to Download and Use Quants

You can download quants by targeting specific size using the Hugging Face CLI.

Click for download commands

1. Install huggingface-cli:

pip install -U "huggingface_hub[cli]"

2. Download a specific quant:

huggingface-cli download ArtusDev/swiss-ai_Apertus-70B-Instruct-2509-EXL3 --revision "5.0bpw_H6" --local-dir ./

EXL3 quants can be run with any inference client that supports EXL3, such as TabbyAPI. Refer to documentation for set up instructions.

Quant Requests

Request EXL3 Quants

See EXL community hub for request guidelines.

Downloads last month: -; Downloads are not tracked for this model. How to track

Model tree for ArtusDev/swiss-ai_Apertus-70B-Instruct-2509-EXL3

Base model

swiss-ai/Apertus-70B-2509

Finetuned

swiss-ai/Apertus-70B-Instruct-2509

Quantized

(12)

this model