# Deploy hexgrad models on dedicated GPUs

1 hexgrad model ready to deploy on GPU capacity reserved for you, from — parameters, covering text-to-speech. Private OpenAI-compatible endpoint, European GPUs, billed per GPU-hour.

| Model | Type | Params | Context | License | Page |
| --- | --- | --- | --- | --- | --- |
| Kokoro-82M | Text-to-speech | — | — | Apache 2.0 | https://sference.com/models/hexgrad/Kokoro-82M.md |

## FAQ

### Which hexgrad models can I deploy on sference?

1 today, most requested first: Kokoro-82M. Any other hexgrad checkpoint or a fine-tune of one can be requested with the form on this page.

### How many GPUs do hexgrad models need?

It depends on the model: the lineup runs from — to — 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 hexgrad models commercially?

1 of the 1 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 deployment: https://sference.com/models/hexgrad#request. All makers: https://sference.com/dedicated.md