TT

f5 tts

TtsGGUF by cstrUpdated 2026-08-02
Download on Hugging Face
Parameters351M
Context—
Layers—
Architecturecrispasr.reference
Smallest quant0.0 GB
Quick answer

f5 tts needs about 0.5 GB of memory at its main file (a 0.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.0 GB to 1.0 GB (F16).

F5‑TTS v1 Base – a 351M‑parameter text‑to‑speech model in GGUF

F5‑TTS is a 351‑billion‑parameter TTS model converted to GGUF. It uses a 22‑layer Diffusion Transformer and Vocos vocoder. The model supports zero‑shot voice cloning from 3‑15 s reference audio and transcript.

Good at

  • Zero‑shot voice cloning
  • High‑fidelity 24 kHz mono PCM output
  • Flow‑matching synthesis

Limits

  • Requires 8 k context for memory estimates
  • No vision support
  • Weights licensed CC‑BY‑NC‑4.0

Best for

  • Voice cloning demos
  • Audio content creation
  • Research on diffusion TTS

Who it’s for. Developers and researchers needing a lightweight TTS model that can clone voices from short audio clips. The GGUF format allows deployment with llama.cpp on consumer hardware.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 0.5 GB
Fits Get file →
F161.0 GB 1.6 GB
Fits Get file →

The unknown quant file is 0.03 GB and needs about 0.5 GB of VRAM at 8 k context. The F16 quant is 1 GB and requires about 1.6 GB of VRAM. For 8 GB VRAM, either quant is suitable; F16 offers better numerical stability.

What GPU do you need for f5 tts?

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 (1.0 GB file, about 1.6 GB in use).

Specifications

Architecture from the GGUF header

Architecturecrispasr.reference
Parameters351M

Source

Quantized bycstr
FamilyTts
Base modelSWivid/F5-TTS
Downloads (HF)1,843
Last updated2026-08-02

Frequently asked questions about f5 tts

How much VRAM does f5 tts need?

About 0.5 GB at its main file with an 8K context window. That is the 0.0 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 f5 tts on an 8 GB GPU?

Yes, with F16: the 1.0 GB file needs about 1.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of f5 tts GGUF?

It depends on the quant: file is 0.0 GB, F16 is 1.0 GB.

Where can I download f5 tts GGUF?

The files are on Hugging Face in the cstr/f5-tts-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 f5 tts use?

Hugging Face lists the license as cc-by-nc-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 F5‑TTS on 8 GB VRAM?

Yes. The F16 quant needs ~1.6 GB VRAM at 8 k context, well below 8 GB.

Does F5‑TTS support voice cloning?

Yes, it can clone voices from 3‑15 s reference audio plus transcript.

What license applies to the weights?

The weights are licensed CC‑BY‑NC‑4.0; the code is MIT.

Other GGUFs of F5-TTS

Similar models

Browse all →

More from cstr

All by cstr →

More Tts models

All Tts →

Other tiny models

All tiny models →