ZO

zonos v0.1 transformer

ZonosGGUF by cstrUpdated 2026-06-21
Download on Hugging Face
Parameters1.62B
Context—
Layers—
Architecturecrispasr.reference
Smallest quant0.0 GB
Quick answer

zonos v0.1 transformer needs about 1.6 GB of memory at Q4_K (a 1.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 5 quants, from 0.0 GB to 3.2 GB (F16).

Zonos v0.1 transformer – 1.62B‑parameter text‑to‑speech model

Zonos v0.1 transformer is a 1.62‑billion‑parameter TTS model trained on over 200k hours of multilingual speech. It supports speaker cloning, emotion control, and fine‑grained speaking rate and pitch adjustments. The model outputs native 44.1 kHz mono PCM audio.

Good at

  • Speaker cloning from short audio clips
  • Emotion control (happiness, sadness, anger, fear)
  • Multilingual TTS (English, Japanese, Chinese, French, German)

Limits

  • Requires a DAC 44.1 kHz decoder GGUF for audio output
  • Runs only on Linux with NVIDIA GPUs 3000‑series or newer, 6 GB+ VRAM
  • No vision support

Best for

  • Generating natural speech for voice assistants
  • Creating custom voice clones for media production
  • Producing multilingual audio content

Who it’s for. Developers and researchers building TTS applications who need expressive, controllable speech synthesis. The model is suitable for projects requiring speaker cloning and emotion modulation.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 0.5 GB
Fits Get file →
—0.0 GB 0.5 GB
Fits Get file →
Q4_K1.0 GB 1.6 GB
Fits Get file →
Q8_01.7 GB 2.4 GB
Fits Get file →
F163.2 GB 4.1 GB
Fits Get file →

For 8 GB VRAM use the Q4_K quant (0.98 GB file, ~1.6 GB memory at 8k context). For 12 GB VRAM use Q8_0 (1.73 GB file, ~2.4 GB memory). For 16 GB VRAM use F16 (3.25 GB file, ~4.1 GB memory).

What GPU do you need for zonos v0.1 transformer?

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 Q8_0 (1.7 GB file, about 2.4 GB in use).
  • 6 GB VRAM: the best quant that fits is F16 (3.2 GB file, about 4.1 GB in use).

Which zonos v0.1 transformer quant should you choose?

Q4_K (1.0 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 the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturecrispasr.reference
Parameters1.62B

Source

Quantized bycstr
FamilyZonos
Licenseapache-2.0
Downloads (HF)1,515
Last updated2026-06-21

Frequently asked questions about zonos v0.1 transformer

How much VRAM does zonos v0.1 transformer need?

About 1.6 GB at Q4_K with an 8K context window. That is the 1.0 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 zonos v0.1 transformer on an 8 GB GPU?

Yes, with F16: the 3.2 GB file needs about 4.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of zonos v0.1 transformer GGUF?

It depends on the quant: file is 0.0 GB, file is 0.0 GB, Q4_K is 1.0 GB, Q8_0 is 1.7 GB, F16 is 3.2 GB.

Where can I download zonos v0.1 transformer GGUF?

The files are on Hugging Face in the cstr/zonos-v0.1-transformer-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 zonos v0.1 transformer 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 Zonos v0.1 on 8 GB VRAM?

Yes, using the Q4_K quantized file which requires about 1.6 GB of VRAM at 8k context.

Does the model support image inputs?

No, Zonos v0.1 is a text‑to‑speech model and does not process vision data.

What license does the model use?

The model is released under the Apache 2.0 license.

Other GGUFs of Zonos-v0.1-transformer

Similar models

Browse all →

More from cstr

All by cstr →

More Zonos models

All Zonos →

Other tiny models

All tiny models →