Deploy Hugging Face models on dedicated GPUs
2 Hugging Face models ready to deploy on GPU capacity reserved for you, from 2.2B to 3.1B parameters, covering chat & reasoning and vision & multimodal. Private OpenAI-compatible endpoint, European GPUs, billed per GPU-hour.
| Model | Type | Params | Context | License |
|---|---|---|---|---|
| Hugging Face | Chat & reasoning | 3.1B | 64K | Apache 2.0 |
SmolVLM2-2.2B-Instructvision Hugging Face | Vision & multimodal | 2.2B | 8K | Apache 2.0 |
Specs from Hugging Face, synced 2026-10-27. Machine-readable version: https://sference.com/models/HuggingFaceTB.md
FAQ
Which Hugging Face models can I deploy on sference?
2 today, most requested first: SmolLM3-3B and SmolVLM2-2.2B-Instruct. Any other Hugging Face checkpoint or a fine-tune of one can be requested with the form on this page.
How many GPUs do Hugging Face models need?
It depends on the model: the lineup runs from 2.2B to 3.1B parameters. Each model page lists the checkpoint size and the minimum footprint on 80 GB and 141 GB GPUs. You don't pick hardware on sference: you choose a performance tier and we size the deployment.
Can I use Hugging Face models commercially?
2 of the 2 listed models are under licenses that allow commercial use (Apache 2.0 across the lineup). Each model page summarizes its license and links the full text.
How is a dedicated deployment priced?
Per GPU-hour on a monthly commitment, sized to your throughput and latency targets.
Request a Hugging Face model
Tell us which Hugging Face model and roughly how much traffic you expect. Fine-tunes of these models work the same way.
- 01We size it
A performance tier, the capacity behind it, and a quote for your volume.
- 02We benchmark it
Bring one workload with a sample of real traffic; we come back with latency and throughput numbers.
- 03It goes live
We provision the deployment. You call it with the same API and model id as before.