# Deploy Apertus-70B-Instruct-2509 on dedicated GPUs

Apertus-70B-Instruct-2509 by Swiss AI Initiative, deployable on sference as a dedicated deployment: reserved GPU capacity, private endpoint, European GPUs, billed per GPU-hour on monthly commitments. Request it at https://sference.com/models/swiss-ai/Apertus-70B-Instruct-2509.

## Specs

- Hugging Face: https://huggingface.co/swiss-ai/Apertus-70B-Instruct-2509
- Category: Chat & reasoning
- Parameters: 71B
- Architecture: Dense
- Context: 64K tokens
- Published precision: BF16
- Checkpoint size: 141 GB
- Minimum footprint: 4 GPUs (80 GB) or 2 GPUs (141 GB) to load the weights; more for long contexts and concurrency
- License: Apache 2.0 (Commercial use allowed)

## FAQ

### Can I run Apertus-70B-Instruct-2509 on a dedicated deployment in Europe?

Yes. sference deploys Apertus-70B-Instruct-2509 on GPU capacity reserved for you, behind a private endpoint, with every request processed on European GPUs and logged in your audit trail. Tell us your expected volume and latency targets with the form on this page and we come back with a sizing and a quote.

### How many GPUs does Apertus-70B-Instruct-2509 need?

The published checkpoint is about 141 GB (BF16), so loading it takes at least 4 GPUs with 80 GB of memory each, or 2 GPUs with 141 GB each. Long contexts and high concurrency need more for the KV cache; quantization needs less. You don't pick hardware on sference: you choose a performance tier and we size the deployment.

### Is Apertus-70B-Instruct-2509 licensed for commercial use?

Apertus-70B-Instruct-2509 is published under the Apache 2.0 license. Permissive: commercial use, modification, and private deployment allowed; keep the license and notices.

### How is a dedicated deployment priced?

Per GPU-hour on a monthly commitment, sized to your throughput and latency targets.

Facts from Hugging Face, synced 2026-10-27. All deployable models: https://sference.com/dedicated.md