MO

moss tts local

MossGGUF by ilintarUpdated 2026-07-27
Download on Hugging Face
Parameters2.23B
Context—
Layers—
Architecturemoss_tts_local
Smallest quant4.5 GB
Quick answer

moss tts local needs about 5.5 GB of memory at Q8_0 (a 4.5 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 2 quants, from 4.5 GB (Q8_0) to 4.6 GB (Q8_0).

MOSS-TTS Local v1.5: 48 kHz stereo text‑to‑speech with voice cloning

MOSS‑TTS Local Transformer v1.5 delivers 48 kHz stereo audio synthesis and zero‑shot voice cloning. It supports 31 languages, explicit pause markers, and stable prosody. The model is released under Apache‑2.0.

Good at

  • High‑fidelity stereo TTS
  • Stable voice cloning
  • Multilingual synthesis with language tags

Limits

  • Requires ~5.5‑5.7 GB VRAM for Q8_0 at 8k context
  • No vision support
  • License is Apache‑2.0

Best for

  • Local TTS applications
  • Voice cloning projects
  • Multilingual audio generation

Who it’s for. Developers building offline TTS systems that need high‑quality stereo output and robust voice cloning. The model is suitable for projects requiring multilingual support and explicit prosody control.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_04.5 GB 5.5 GB
Fits Get file →
Q8_04.6 GB 5.7 GB
Fits Get file →

The available GGUF files are Q8_0. The 4.46 GB file uses about 5.5 GB VRAM at 8k context; the 4.65 GB file uses about 5.7 GB VRAM. For 8 GB VRAM, the 4.46 GB file is recommended. Memory estimates are approximate.

What GPU do you need for moss tts local?

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 (4.6 GB file, about 5.7 GB in use).

Which moss tts local quant should you choose?

Q8_0 (4.5 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

Architecturemoss_tts_local
Parameters2.23B

Source

Quantized byilintar
FamilyMoss
Licenseapache-2.0
Downloads (HF)2,662
Last updated2026-07-27

Frequently asked questions about moss tts local

How much VRAM does moss tts local need?

About 5.5 GB at Q8_0 with an 8K context window. That is the 4.5 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 local on an 8 GB GPU?

Yes, with Q8_0: the 4.6 GB file needs about 5.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of moss tts local GGUF?

It depends on the quant: Q8_0 is 4.5 GB, Q8_0 is 4.6 GB.

Where can I download moss tts local GGUF?

The files are on Hugging Face in the ilintar/moss-tts-local-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 local 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 this model on 8 GB VRAM?

Yes, the 4.46 GB Q8_0 file uses about 5.5 GB VRAM at 8k context, leaving headroom for other processes.

Does this model support vision tasks?

No, it is a text‑to‑speech model only.

What license applies to the GGUF weights?

The weights are licensed under Apache‑2.0, matching the source models.

Other GGUFs of MOSS-TTS-Local-Transformer-v1.5

Similar models

Browse all →

More from ilintar

All by ilintar →

More Moss models

All Moss →

Other tiny models

All tiny models →