MO

Moss Tts Local

MossGGUF by John9007Updated 2026-04-14
Download on Hugging Face
Parameters2.74B
Context40K
Layers28
Architecturemoss-tts-delay
Smallest quant1.1 GB
Quick answer

Moss Tts Local needs about 3.4 GB of memory at Q4_K_M (a 1.9 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 1.1 GB (Q2_K) to 1.9 GB (Q4_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.

Moss Tts Local: lightweight 2.74B parameter TTS model in GGUF format

Moss Tts Local is a 2.74B parameter text‑to‑speech model quantized for local deployment. It supports high‑fidelity speech synthesis and is available in three GGUF quantizations. The model is licensed under apache-2.0 and designed for edge/on‑device use.

Good at

  • High‑fidelity local TTS
  • Low‑memory deployment
  • Stable long‑form speech

Limits

  • No vision support
  • Limited to 40960 context tokens
  • No multilingual support listed

Best for

  • Edge TTS applications
  • Voice cloning pipelines
  • Real‑time TTS on low‑resource devices

Who it’s for. Developers building on‑device TTS solutions who need a small, open‑source model. The model is suitable for integration into mobile or embedded systems where GPU memory is limited.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.1 GB 2.6 GB
Fits Get file →
Q3_K_M1.4 GB 2.8 GB
Fits Get file →
Q4_K_M1.9 GB 3.4 GB
Fits Get file →

For 8 GB VRAM, Q2_K (1.14 GB file, 2.6 GB memory at 8 k context) is recommended. If more memory is available, Q3_K_M (1.41 GB, 2.8 GB) or Q4_K_M (1.94 GB, 3.4 GB) can be used for slightly higher quality.

What GPU do you need for Moss Tts Local?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) 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_M (1.9 GB file, about 3.4 GB in use).

Which Moss Tts Local quant should you choose?

Q4_K_M is the usual starting point for Moss Tts Local: it balances file size and quality well. Here it is a 1.9 GB file.

If memory is tight, the smallest file is Q2_K at 1.1 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturemoss-tts-delay
Parameters2.74B
Layers28
Trained context40,960 tokens
KV cache (fp16)112 KB per token

Source

Quantized byJohn9007
FamilyMoss
Licenseapache-2.0
Downloads (HF)828
Last updated2026-04-14

Frequently asked questions about Moss Tts Local

How much VRAM does Moss Tts Local need?

About 3.4 GB at Q4_K_M with an 8K context window. That is the 1.9 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 Q4_K_M: the 1.9 GB file needs about 3.4 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: Q2_K is 1.1 GB, Q3_K_M is 1.4 GB, Q4_K_M is 1.9 GB.

What context length does Moss Tts Local support?

The GGUF header lists a trained context length of 40,960 tokens (40K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.

Where can I download Moss Tts Local GGUF?

The files are on Hugging Face in the John9007/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 Moss Tts Local on 8 GB VRAM?

Yes, the Q2_K quantization uses 2.6 GB of VRAM at 8 k context, fitting comfortably in 8 GB.

Does Moss Tts Local support multiple languages?

The model’s language list is empty, so no explicit multilingual support is provided.

Other GGUFs of MOSS-TTS-Local-Transformer

Similar models

Browse all →

More Moss models

All Moss →

Other tiny models

All tiny models →