MO

moss tts

MossGGUF by ilintarUpdated 2026-08-21
Download on Hugging Face
Parameters2.04B
Context—
Layers—
Architecturemoss_tts_delay
Smallest quant4.1 GB
Quick answer

moss tts needs about 5.1 GB of memory at its main file (a 4.1 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 4 quants, from 4.1 GB (Q8_0) to 16.4 GB.

MOSS‑TTS v1.5 GGUF model for multilingual text‑to‑speech

MOSS‑TTS v1.5 is a 2.04‑billion‑parameter TTS model that supports 31 languages. It offers zero‑shot voice cloning, long‑form speech generation, and token‑level duration control. The GGUF weights are available in Q8_0 precision for efficient inference.

Good at

  • Zero‑shot voice cloning
  • Long‑form speech generation
  • Explicit pause control

Limits

  • No vision support
  • Requires BF16/FP32 codec‑sidecar runtime
  • Large memory footprint for full BF16

Best for

  • Multilingual TTS applications
  • Voice cloning for synthetic assistants
  • Generating long audio passages

Who it’s for. Developers building multilingual TTS services or voice‑clone applications. The model is suitable for users who need high‑quality speech synthesis across many languages and can run the required GGUF runtime.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_04.1 GB 5.1 GB
Fits Get file →
—4.1 GB 5.1 GB
Fits Get file →
Q8_09.3 GB 11.0 GB
Too big Get file →
—16.4 GB 18.9 GB
Too big Get file →

For 8‑GB VRAM use the 4.09‑GB Q8_0 file (≈5.1 GB memory at 8 k context). For 16‑GB VRAM use the 9.34‑GB Q8_0 file (≈11 GB memory). Larger VRAM allows the 16.45‑GB Q8_0 file (≈18.9 GB memory).

What GPU do you need for moss 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: no quant fits at an 8K context.
  • 6 GB VRAM: the best quant that fits is Q8_0 (4.1 GB file, about 5.1 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (4.1 GB file, about 5.1 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (9.3 GB file, about 11.0 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (9.3 GB file, about 11.0 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (16.4 GB file, about 18.9 GB in use).

Which moss tts quant should you choose?

If memory is tight, the smallest file is Q8_0 at 4.1 GB, with the quality trade-offs that come with fewer bits. 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

Architecturemoss_tts_delay
Parameters2.04B

Source

Quantized byilintar
FamilyMoss
Licenseapache-2.0
Downloads (HF)3,477
Last updated2026-08-21

Frequently asked questions about moss tts

How much VRAM does moss tts need?

About 5.1 GB at its main file with an 8K context window. That is the 4.1 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 moss tts on an 8 GB GPU?

Yes, with Q8_0: the 4.1 GB file needs about 5.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of moss tts GGUF?

It depends on the quant: Q8_0 is 4.1 GB, file is 4.1 GB, Q8_0 is 9.3 GB, file is 16.4 GB.

Where can I download moss tts GGUF?

The files are on Hugging Face in the ilintar/moss-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 moss tts 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 MOSS‑TTS on 8 GB VRAM?

Yes, the 4.09‑GB Q8_0 GGUF file requires about 5.1 GB memory at 8 k context, fitting within 8 GB VRAM.

Does MOSS‑TTS support voice cloning?

Yes, it offers zero‑shot voice cloning with improved speaker similarity and reduced variance.

What runtime is needed for the GGUF files?

An OpenMOSS build that supports BF16/FP32 codec‑sidecar loading is required; older builds that expect FP16 tensors cannot load these files.

Other GGUFs of MOSS-TTS-v1.5

Similar models

Browse all →

More from ilintar

All by ilintar →

More Moss models

All Moss →

Other tiny models

All tiny models →