moss tts v1.5 needs about 10.3 GB of memory at Q6_K (a 8.8 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 5 quants, from 3.5 GB to 17.0 GB (F16).
MOSS TTS v1.5 – a 1.77B parameter audio codec for TTS
MOSS TTS v1.5 is a 1.77B parameter audio codec built on the moss-tts-codec architecture. It uses a 32‑layer Residual Vector Quantizer to compress 24kHz audio to 12.5Hz. The model is released under Apache‑2.0 and is available in several GGUF quantisations.
Good at
- High‑fidelity audio compression
- Semantic‑rich tokenisation
- End‑to‑end TTS synthesis
Limits
- No vision support
- Requires 8k context for memory estimates
- No explicit language list
Best for
- Audio generation in low‑latency settings
- Speech synthesis for ASR pipelines
- Audio reconstruction tasks
Who it’s for. Developers building TTS or audio generation systems that need a lightweight, transformer‑based codec. The model is suitable for projects that can run GGUF weights on GPU or CPU with sufficient VRAM.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 3.5 GB | 4.5 GB | Fits | Get file → | |
| Q4_K | 7.0 GB | 8.3 GB | Too big | Get file → | |
| Q6_K | 8.8 GB | 10.3 GB | Too big | Get file → | |
| Q8_0 | 10.5 GB | 12.2 GB | Too big | Get file → | |
| F16 | 17.0 GB | 19.5 GB | Too big | Get file → |
For 8 GB VRAM use the Q4_K quant (7 GB file, ~8.3 GB memory). With 12 GB VRAM the Q6_K quant (8.79 GB file, ~10.3 GB memory) is appropriate. For higher precision and more VRAM, Q8_0 (10.47 GB file, ~12.2 GB memory) or F16 (16.99 GB file, ~19.5 GB memory) can be used.
What GPU do you need for moss tts 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: no quant fits at an 8K context.
- 6 GB VRAM: the best quant that fits is the main file (3.5 GB file, about 4.5 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (3.5 GB file, about 4.5 GB in use).
- 12 GB VRAM: the best quant that fits is Q6_K (8.8 GB file, about 10.3 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (10.5 GB file, about 12.2 GB in use).
- 24 GB VRAM: the best quant that fits is F16 (17.0 GB file, about 19.5 GB in use).
Which moss tts v1.5 quant should you choose?
Q6_K (8.8 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.
If memory is tight, the smallest file is the first one in the table at 3.5 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
Source
Frequently asked questions about moss tts v1.5
How much VRAM does moss tts v1.5 need?
About 10.3 GB at Q6_K with an 8K context window. That is the 8.8 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 v1.5 on an 8 GB GPU?
Yes, with the smaller files: the 3.5 GB file needs about 4.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of moss tts v1.5 GGUF?
It depends on the quant: file is 3.5 GB, Q4_K is 7.0 GB, Q6_K is 8.8 GB, Q8_0 is 10.5 GB, F16 is 17.0 GB.
Where can I download moss tts v1.5 GGUF?
The files are on Hugging Face in the cstr/moss-tts-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 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 v1.5 on 8 GB VRAM?
Yes, the Q4_K quantisation requires about 8.3 GB memory at 8k context, which fits in 8 GB VRAM with some overhead.
Does this model support multiple languages?
The model card does not list supported languages; no language information is provided.
What license applies to the GGUF weights?
The GGUF weights are distributed under Apache‑2.0, inherited from the upstream model.