SU

supertonic 3

SupertonicGGUF by cstrUpdated 2026-09-13
Download on Hugging Face
Parameters100M
Context—
Layers—
Architecturesupertonic-tts
Smallest quant0.2 GB
Quick answer

supertonic 3 needs about 0.7 GB of memory at F16 (a 0.2 GB file) with an 8K context window, so it fits on a 4 GB GPU.

Supertonic 3 – lightweight on‑device text‑to‑speech

Supertonic 3 is a compact TTS model with 0.0995 billion parameters. It supports 31 languages and runs entirely on device using ONNX Runtime. The model is available in a single F16 GGUF file.

Good at

  • 31‑language support
  • Stable reading with fewer repeats
  • High speaker similarity across shared languages

Limits

  • Requires ~0.7 GB VRAM at 8k context
  • No vision or multimodal capabilities
  • OpenRAIL license with use restrictions

Best for

  • Local TTS for mobile apps
  • Voice assistants needing quick synthesis
  • Custom voice style creation with Voice Builder

Who it’s for. Developers building on‑device speech synthesis solutions that need a small footprint and multi‑language coverage. The model is suitable for applications where cloud calls are undesirable.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F160.2 GB 0.7 GB
Fits Get file →

The only available quantization is F16, with a file size of 0.2 GB. It requires approximately 0.7 GB of VRAM at an 8k context length. This is the recommended choice for devices with at least 1 GB of VRAM.

What GPU do you need for supertonic 3?

These figures add the file size, an fp16 KV cache at an 8K context window and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is F16 (0.2 GB file, about 0.7 GB in use).

Which supertonic 3 quant should you choose?

F16 (0.2 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturesupertonic-tts
Parameters100M

Source

Quantized bycstr
Licenseopenrail
Downloads (HF)1,948
Last updated2026-09-13

Frequently asked questions about supertonic 3

How much VRAM does supertonic 3 need?

About 0.7 GB at F16 with an 8K context window. That is the 0.2 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run supertonic 3 on an 8 GB GPU?

Yes, with F16: the 0.2 GB file needs about 0.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of supertonic 3 GGUF?

It depends on the quant: F16 is 0.2 GB.

Where can I download supertonic 3 GGUF?

The files are on Hugging Face in the cstr/supertonic-3-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does supertonic 3 use?

Hugging Face lists the license as openrail. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run Supertonic 3 on a device with 8 GB VRAM?

Yes. The F16 quantization needs about 0.7 GB of VRAM at 8k context, well below 8 GB.

Does Supertonic 3 support custom voice styles?

Yes, the GGUF file includes ten preset voices and can be extended with Voice Builder embeddings.

What license applies to Supertonic 3?

The model is licensed under OpenRAIL‑M with use restrictions; commercial use is permitted under those terms.

Similar models

Browse all →

More from cstr

All by cstr →

More Supertonic models

All Supertonic →

Other tiny models

All tiny models →