MOSS TTS Local Transformer v1.5 needs about 7.2 GB of memory at Q8_0 (a 6.0 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 4 quants, from 0.0 GB to 9.4 GB (F16).
MOSS TTS Local Transformer v1.5 – 2.12B parameter text‑to‑speech model
MOSS TTS Local Transformer v1.5 is a 2.12B parameter RQ‑Transformer model that generates 48 kHz stereo audio. It supports 31 languages, zero‑shot voice cloning, long‑form speech, and explicit pause control. The model is released under Apache‑2.0.
Good at
- High‑fidelity stereo audio
- Stable multilingual synthesis
- Explicit pause markers
Limits
- No vision support
- Requires 8 k context for memory estimates
- Large VRAM needed for full precision
Best for
- Voice cloning projects
- Multilingual TTS applications
- Audio content creation
Who it’s for. Developers and researchers needing a local, high‑quality TTS engine that runs on ggml. The model is suitable for applications that require precise control over prosody and speaker similarity.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q8_0 | 6.0 GB | 7.2 GB | Fits | Get file → | |
| F32 | 8.5 GB | 10.0 GB | Too big | Get file → | |
| F16 | 9.4 GB | 11.0 GB | Too big | Get file → |
For 8 GB VRAM, use the Q8_0 quant (file size 5.97 GB, estimated memory 7.2 GB at 8 k context). If more VRAM is available, the F32 quant (8.49 GB, 10 GB memory) gives the highest fidelity. The unknown quant is 0.01 GB but memory usage is not specified.
What GPU do you need for MOSS TTS Local Transformer v1.5?
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 the main file (0.0 GB file, about 0.5 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 0.5 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (6.0 GB file, about 7.2 GB in use).
- 12 GB VRAM: the best quant that fits is F16 (9.4 GB file, about 11.0 GB in use).
Which MOSS TTS Local Transformer v1.5 quant should you choose?
Q8_0 (6.0 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.
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
Frequently asked questions about MOSS TTS Local Transformer v1.5
How much VRAM does MOSS TTS Local Transformer v1.5 need?
About 7.2 GB at Q8_0 with an 8K context window. That is the 6.0 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 MOSS TTS Local Transformer v1.5 on an 8 GB GPU?
Yes, with Q8_0: the 6.0 GB file needs about 7.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of MOSS TTS Local Transformer v1.5 GGUF?
It depends on the quant: file is 0.0 GB, Q8_0 is 6.0 GB, F32 is 8.5 GB, F16 is 9.4 GB.
Where can I download MOSS TTS Local Transformer v1.5 GGUF?
The files are on Hugging Face in the mudler/MOSS-TTS-Local-Transformer-v1.5-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 Transformer v1.5 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 Transformer v1.5 on 8 GB VRAM?
Yes, the Q8_0 quant requires about 7.2 GB of VRAM at 8 k context, which fits within 8 GB.
Does the model support voice cloning?
Yes, it offers zero‑shot voice cloning with improved speaker similarity and reduced variance.
What languages are supported?
The model supports 31 languages, including English, French, Chinese, and many others.