OU

outetts 0.3 1b

OutettsGGUF by cstrUpdated 2026-08-02
Download on Hugging Face
Parameters1.19B
Context—
Layers—
Architecturewavtokenizer
Smallest quant0.1 GB
Quick answer

outetts 0.3 1b needs about 1.4 GB of memory at Q4_K (a 0.8 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 5 quants, from 0.1 GB (F16) to 2.4 GB (F16).

OuteTTS 0.3 1B – 1.19B‑parameter text‑to‑speech model

OuteTTS 0.3 1B is a 1.19‑billion‑parameter wavtokenizer model that supports English, Japanese, Korean, Chinese, French, and German. It adds punctuation handling and experimental voice control. The model is released under CC‑BY‑NC‑SA‑4.0.

Good at

  • High‑quality speech synthesis
  • Punctuation‑aware output
  • Multilingual support

Limits

  • No vision support
  • Non‑commercial license
  • Requires CrispASR commit cbe208fa for Q4_K

Best for

  • Embedding TTS in LLM applications
  • Generating synthetic voice for demos
  • Adding speech to chatbots

Who it’s for. Developers building text‑to‑speech features into language models. The model is compatible with llama.cpp and CrispASR and can be used in research or non‑commercial projects that respect the CC‑BY‑NC‑SA‑4.0 license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F160.1 GB 0.6 GB
Fits Get file →
Q5_K0.8 GB 1.4 GB
Fits Get file →
Q4_K0.8 GB 1.4 GB
Fits Get file →
Q8_01.3 GB 1.9 GB
Fits Get file →
F162.4 GB 3.2 GB
Fits Get file →

For 8 GB VRAM, use Q5_K (file size 0.82 GB, estimated 1.4 GB memory). For 4 GB VRAM, use Q4_K (file size 0.84 GB, estimated 1.4 GB memory). If memory is limited, the F16 0.13 GB file uses only 0.6 GB memory at 8 k context.

What GPU do you need for outetts 0.3 1b?

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 (2.4 GB file, about 3.2 GB in use).

Which outetts 0.3 1b quant should you choose?

Q4_K (0.8 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

If memory is tight, the smallest file is F16 at 0.1 GB, with the quality trade-offs that come with fewer bits. 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

Architecturewavtokenizer
Parameters1.19B

Source

Quantized bycstr
FamilyOutetts
Downloads (HF)1,443
Last updated2026-08-02

Frequently asked questions about outetts 0.3 1b

How much VRAM does outetts 0.3 1b need?

About 1.4 GB at Q4_K with an 8K context window. That is the 0.8 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 outetts 0.3 1b on an 8 GB GPU?

Yes, with F16: the 2.4 GB file needs about 3.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of outetts 0.3 1b GGUF?

It depends on the quant: F16 is 0.1 GB, Q5_K is 0.8 GB, Q4_K is 0.8 GB, Q8_0 is 1.3 GB, F16 is 2.4 GB.

Where can I download outetts 0.3 1b GGUF?

The files are on Hugging Face in the cstr/outetts-0.3-1b-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 outetts 0.3 1b use?

Hugging Face lists the license as cc-by-nc-sa-4.0. 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 this model on 4 GB VRAM?

Yes, the Q4_K quant uses 0.84 GB file size and estimates 1.4 GB memory at 8 k context, which fits 4 GB VRAM.

Does this model support voice control?

Experimental voice control is included but may be inconsistent due to limited data.

Is commercial use allowed?

No, the CC‑BY‑NC‑SA‑4.0 license prohibits commercial use and requires share‑alike attribution.

Other GGUFs of OuteTTS-0.3-1B

Similar models

Browse all →

More from cstr

All by cstr →

More Outetts models

All Outetts →

Other tiny models

All tiny models →