MO

MOSS TTS Realtime

MossGGUF by BricksDisplayUpdated 2026-10-21
Download on Hugging Face
Parameters2.08B
Context40K
Layers28
Architectureqwen3
Smallest quant0.8 GB
Quick answer

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 7.7 GB (F32). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.

MOSS‑TTS‑Realtime: real‑time streaming TTS for Chinese and English

MOSS‑TTS‑Realtime is a context‑aware, multi‑turn streaming TTS model. It runs with a model file and a codec file in llama.cpp. The model supports real‑time voice agents with dialogue history conditioning.

Good at

  • Real‑time streaming TTS
  • Multi‑turn dialogue support
  • Chinese and English voice synthesis

Limits

  • Requires two files (model + codec)
  • Lower‑precision quants reduce intelligibility
  • No vision or image generation

Best for

  • Voice‑assistant applications
  • Live podcast narration
  • Interactive chatbot audio

Who it’s for. Developers building offline or online TTS services that need real‑time, multi‑turn dialogue. The model is suitable for CPU or GPU (CUDA, Vulkan, Metal) deployments using llama.cpp or codec.cpp.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.8 GB 2.2 GB
Fits Get file →
Q3_K_S0.9 GB 2.3 GB
Fits Get file →
Q3_K_M0.9 GB 2.4 GB
Fits Get file →
Q3_K_L1.0 GB 2.4 GB
Fits Get file →
Q4_01.1 GB 2.5 GB
Fits Get file →
Q4_K_S1.1 GB 2.5 GB
Fits Get file →
Q4_K_M1.1 GB 2.5 GB
Fits Get file →
Q4_11.1 GB 2.6 GB
Fits Get file →
Q5_01.2 GB 2.7 GB
Fits Get file →
Q5_K_S1.2 GB 2.7 GB
Fits Get file →
Q5_K_M1.3 GB 2.7 GB
Fits Get file →
Q5_11.3 GB 2.8 GB
Fits Get file →
Q6_K1.4 GB 2.9 GB
Fits Get file →
Q4_K_M1.6 GB 3.0 GB
Fits Get file →
Q5_K_M1.8 GB 3.3 GB
Fits Get file →
Q8_01.8 GB 3.3 GB
Fits Get file →
Q8_02.5 GB 3.9 GB
Fits Get file →
BF163.4 GB 4.9 GB
Fits Get file →
F163.4 GB 4.9 GB
Fits Get file →
F164.2 GB 5.6 GB
Fits Get file →
F326.9 GB 8.3 GB
Too big Get file →
F327.7 GB 9.1 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (file size 1.11 GB, memory 2.5 GB). For 16 GB VRAM, Q5_K_M (1.26 GB, 2.7 GB) or Q6_K (1.42 GB, 2.9 GB) provide higher quality. For maximum fidelity, BF16 (3.45 GB, 4.9 GB) is recommended if memory allows.

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 F16 (4.2 GB file, about 5.6 GB in use).
  • 12 GB VRAM: the best quant that fits is F32 (7.7 GB file, about 9.1 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

Architectureqwen3
Parameters2.08B
Layers28
Trained context40,960 tokens
KV cache (fp16)112 KB per token

Source

Quantized byBricksDisplay
FamilyMoss
Licenseapache-2.0
Downloads (HF)3,220
Last updated2026-10-21

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 F16: the 4.2 GB file needs about 5.6 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 BricksDisplay/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, a Q4_K_M quant uses about 2.5 GB of VRAM at 8 k context, which fits within 8 GB. Lower quants use less VRAM but may reduce quality.

Does the model support voice cloning?

Yes, the codec file includes speaker encoders that enable zero‑shot voice cloning from short reference audio.

What license applies to this model?

The model is released under apache‑2.0, the same as the original OpenMOSS model.

Other GGUFs of MOSS-TTS-Realtime

Similar models

Browse all →

More from BricksDisplay

All by BricksDisplay →

More Moss models

All Moss →

Other tiny models

All tiny models →