MOSS TTS Realtime needs about 2.5 GB of memory at Q4_K_M (a 1.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 22 quants, from 0.8 GB (Q2_K) to 6.9 GB (F32). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.
MOSS TTS Realtime – 2.08B Qwen3 backbone for real‑time speech synthesis
MOSS TTS Realtime is a 2.08B parameter Qwen3 model converted to GGUF. It supports real‑time text‑to‑speech with a 4‑layer depth decoder and 17‑channel audio emission. The model is licensed under apache‑2.0 and runs on llama.cpp and codec.cpp.
Good at
- Real‑time TTS
- High‑fidelity audio generation
- Multilingual support
Limits
- No vision support
- Requires 8k context for full performance
- Large memory for higher quants
Best for
- Live streaming narration
- Interactive voice assistants
- Real‑time dubbing
Who it’s for. Developers building real‑time TTS applications who need a lightweight, open‑source model. The model is suitable for projects that can run on a GPU with at least 8 GB VRAM and support the Qwen3 architecture.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 0.8 GB | 2.2 GB | Fits | Get file → | |
| Q3_K_S | 0.9 GB | 2.3 GB | Fits | Get file → | |
| Q3_K_M | 0.9 GB | 2.4 GB | Fits | Get file → | |
| Q3_K_L | 1.0 GB | 2.4 GB | Fits | Get file → | |
| Q4_0 | 1.1 GB | 2.5 GB | Fits | Get file → | |
| Q4_K_S | 1.1 GB | 2.5 GB | Fits | Get file → | |
| Q4_K_M | 1.1 GB | 2.5 GB | Fits | Get file → | |
| Q4_1 | 1.1 GB | 2.6 GB | Fits | Get file → | |
| Q5_0 | 1.2 GB | 2.7 GB | Fits | Get file → | |
| Q5_K_S | 1.2 GB | 2.7 GB | Fits | Get file → | |
| Q5_K_M | 1.3 GB | 2.7 GB | Fits | Get file → | |
| Q5_1 | 1.3 GB | 2.8 GB | Fits | Get file → | |
| Q6_K | 1.4 GB | 2.9 GB | Fits | Get file → | |
| Q4_K_M | 1.6 GB | 3.0 GB | Fits | Get file → | |
| Q5_K_M | 1.8 GB | 3.3 GB | Fits | Get file → | |
| Q8_0 | 1.8 GB | 3.3 GB | Fits | Get file → | |
| Q8_0 | 2.5 GB | 3.9 GB | Fits | Get file → | |
| BF16 | 3.4 GB | 4.9 GB | Fits | Get file → | |
| F16 | 3.4 GB | 4.9 GB | Fits | Get file → | |
| F16 | 4.2 GB | 5.6 GB | Fits | Get file → | |
| F32 | 6.4 GB | 7.9 GB | Tight | Get file → | |
| F32 | 6.9 GB | 8.3 GB | Too big | Get file → |
For 8 GB VRAM use Q4_K_M (file size 1.11 GB, estimated 2.5 GB memory). For 12 GB VRAM use Q5_K_M (1.26 GB, 2.7 GB). For 16 GB VRAM use Q6_K (1.42 GB, 2.9 GB). Higher quants increase memory usage accordingly.
What GPU do you need for MOSS TTS Realtime?
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 Q8_0 (2.5 GB file, about 3.9 GB in use).
- 6 GB VRAM: the best quant that fits is F16 (4.2 GB file, about 5.6 GB in use).
- 8 GB VRAM: the best quant that fits is F32 (6.4 GB file, about 7.9 GB in use).
- 12 GB VRAM: the best quant that fits is F32 (6.9 GB file, about 8.3 GB in use).
Which MOSS TTS Realtime quant should you choose?
Q4_K_M is the usual starting point for MOSS TTS Realtime: it balances file size and quality well. Here it is a 1.1 GB file.
The Q8_0 file is 1.8 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q2_K at 0.8 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
Source
Frequently asked questions about MOSS TTS Realtime
How much VRAM does MOSS TTS Realtime need?
About 2.5 GB at Q4_K_M with an 8K context window. That is the 1.1 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 Realtime on an 8 GB GPU?
Yes, with F32: the 6.4 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of MOSS TTS Realtime GGUF?
It depends on the quant: Q2_K is 0.8 GB, Q3_K_S is 0.9 GB, Q3_K_M is 0.9 GB, Q3_K_L is 1.0 GB, Q4_0 is 1.1 GB, Q4_K_S is 1.1 GB and 16 more.
What context length does MOSS TTS Realtime 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 Realtime GGUF?
The files are on Hugging Face in the Yanlis/MOSS-TTS-Realtime-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 Realtime 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 Realtime on 8 GB VRAM?
Yes, the Q4_K_M quant uses about 2.5 GB memory at 8k context, fitting within 8 GB VRAM.
What is the maximum context length supported?
The model was trained with 40960 tokens, but llama.cpp limits it to 8k context for full performance.
Is the model open source?
Yes, it is released under the apache‑2.0 license and available on Hugging Face.