CH

Chatterbox TTS Persian

ChatterboxGGUF by mazrbaUpdated 2026-07-04
Download on Hugging Face
Parameters264M
Context—
Layers—
Architecturechatterbox-s3gen
Smallest quant0.4 GB
Quick answer

Chatterbox TTS Persian needs about 0.9 GB of memory at Q8_0 (a 0.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.4 GB (Q8_0) to 1.1 GB (F16).

Chatterbox TTS Persian – 0.264B parameter TTS model for Persian

Chatterbox TTS Persian is a 0.264B parameter text‑to‑speech model. It uses a 30‑layer Llama‑AR T3 encoder and an S3Gen decoder to produce 24 kHz WAV audio. The model is released under the MIT license and is available as GGUF files.

Good at

  • Persian text‑to‑speech
  • High‑quality voice synthesis
  • Open‑source licensing

Limits

  • No vision support
  • Requires two GGUF files
  • No other languages supported

Best for

  • Creating Persian audio content
  • Integrating Persian TTS into applications
  • Generating Persian voice data for ASR

Who it’s for. Developers building Persian language voice applications or researchers needing an open‑source Persian TTS pipeline. The model is suitable for projects that require a single‑voice cloning solution in Persian.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_00.4 GB 0.9 GB
Fits Get file →
F161.1 GB 1.8 GB
Fits Get file →

For systems with limited memory, use the Q8_0 quantized file (0.36 GB, ~0.9 GB RAM at 8 k context). If more memory is available, the F16 quantized file (1.14 GB, ~1.8 GB RAM) provides higher precision.

What GPU do you need for Chatterbox TTS Persian?

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 (1.1 GB file, about 1.8 GB in use).

Which Chatterbox TTS Persian quant should you choose?

Q8_0 (0.4 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturechatterbox-s3gen
Parameters264M

Source

Quantized bymazrba
Licensemit
Downloads (HF)1,707
Last updated2026-07-04

Frequently asked questions about Chatterbox TTS Persian

How much VRAM does Chatterbox TTS Persian need?

About 0.9 GB at Q8_0 with an 8K context window. That is the 0.4 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 Chatterbox TTS Persian on an 8 GB GPU?

Yes, with F16: the 1.1 GB file needs about 1.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Chatterbox TTS Persian GGUF?

It depends on the quant: Q8_0 is 0.4 GB, F16 is 1.1 GB.

Where can I download Chatterbox TTS Persian GGUF?

The files are on Hugging Face in the mazrba/Chatterbox-TTS-Persian-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 Chatterbox TTS Persian use?

Hugging Face lists the license as mit. 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 Chatterbox TTS Persian on 8 GB VRAM?

Yes. The Q8_0 quantized model requires about 0.9 GB RAM at 8 k context, well within an 8 GB VRAM budget.

Do I need any other files to use this model?

Yes. Two GGUF files are required: the T3 text‑to‑speech token model and the S3Gen decoder model.

Is the model multilingual?

No. This model is specifically for Persian and does not support other languages.

Other GGUFs of chatterbox

Similar models

Browse all →

More from mazrba

All by mazrba →

More Chatterbox models

All Chatterbox →

Other tiny models

All tiny models →