FI

fireredtts3

FireredttsGGUF by cstrUpdated 2026-09-13
Download on Hugging Face
Parameters2.12B
Context—
Layers—
Architecturefireredtts3-redae
Smallest quant1.1 GB
Quick answer

fireredtts3 needs about 3.2 GB of memory at Q4_K (a 2.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 1.1 GB (F16) to 4.5 GB (F16).

FireRedTTS3: Unified multilingual speech generation and editing

FireRedTTS3 is a unified speech generation and editing system built on semantically enriched continuous speech representations. It supports zero‑shot voice cloning across 24 languages and 21 Chinese dialects, and offers instruction‑controlled voice design and free‑form speech editing.

Good at

  • Zero‑shot voice cloning in 24 languages
  • Instruction‑controlled voice design
  • Free‑form semantic and acoustic editing

Limits

  • No vision support
  • Requires 8k context for memory estimates
  • Apache‑2.0 license

Best for

  • Multilingual TTS applications
  • Voice cloning for diverse dialects
  • Editing speech with natural‑language instructions

Who it’s for. Developers building multilingual TTS systems or voice editing tools. Researchers needing a unified model for speech generation and editing across many languages and dialects.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F161.1 GB 1.7 GB
Fits Get file →
Q4_K2.4 GB 3.2 GB
Fits Get file →
F164.5 GB 5.5 GB
Fits Get file →

For 8 GB VRAM, the Q4_K quantized model (2.43 GB, ~3.2 GB memory at 8k context) is recommended. If more VRAM is available, the F16 model (1.09 GB, ~1.7 GB memory) offers higher precision. The larger F16 variant (4.46 GB, ~5.5 GB memory) requires more memory but provides the highest fidelity.

What GPU do you need for fireredtts3?

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 Q4_K (2.4 GB file, about 3.2 GB in use).
  • 6 GB VRAM: the best quant that fits is F16 (4.5 GB file, about 5.5 GB in use).

Which fireredtts3 quant should you choose?

Q4_K (2.4 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 1.1 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

Architecturefireredtts3-redae
Parameters2.12B

Source

Quantized bycstr
Licenseapache-2.0
Downloads (HF)1,360
Last updated2026-09-13

Frequently asked questions about fireredtts3

How much VRAM does fireredtts3 need?

About 3.2 GB at Q4_K with an 8K context window. That is the 2.4 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 fireredtts3 on an 8 GB GPU?

Yes, with F16: the 4.5 GB file needs about 5.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of fireredtts3 GGUF?

It depends on the quant: F16 is 1.1 GB, Q4_K is 2.4 GB, F16 is 4.5 GB.

Where can I download fireredtts3 GGUF?

The files are on Hugging Face in the cstr/fireredtts3-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 fireredtts3 use?

Hugging Face lists the license as apache-2.0. 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 FireRedTTS3 on 8 GB VRAM?

Yes, the Q4_K quantized version is 2.43 GB and estimates ~3.2 GB memory at 8k context, fitting within 8 GB VRAM.

Does FireRedTTS3 support voice cloning in Chinese dialects?

Yes, it supports zero‑shot voice cloning across 21 Chinese dialects such as Anhui, Fujian, and Wu.

What license applies to FireRedTTS3?

The model is released under the Apache‑2.0 license.

Similar models

Browse all →

More from cstr

All by cstr →

Other tiny models

All tiny models →