qwen3 tts 0.6b base needs about 1.6 GB of memory at Q8_0 (a 1.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 0.5 GB (Q4_K) to 1.8 GB.
Qwen3‑TTS 0.6B Base – multilingual voice‑cloning TTS
Qwen3‑TTS 0.6B Base is a 0.915 billion‑parameter text‑to‑speech model. It supports 10 languages and real‑time streaming synthesis. The model is available in GGUF format for llama.cpp and CrispASR.
Good at
- Real‑time voice cloning
- Multilingual synthesis
- Low‑latency streaming
Limits
- No vision support
- Requires separate tokenizer/codec GGUF
- License is Apache‑2.0
Best for
- Voice‑cloning demos
- Multilingual TTS applications
- Real‑time interactive voice synthesis
Who it’s for. Developers building voice‑cloning or multilingual TTS systems. The model is suitable for research and production use where a lightweight, open‑source solution is needed.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K | 0.5 GB | 1.1 GB | Fits | Get file → | |
| Q8_0 | 1.0 GB | 1.6 GB | Fits | Get file → | |
| — | 1.8 GB | 2.6 GB | Fits | Get file → |
For best quality use the Q8_0 quantised file (0.99 GB, ~1.6 GB RAM at 8k context). If disk space is limited, the Q4_K file (0.53 GB, ~1.1 GB RAM at 8k context) is available but quality is lower. The unknown quant is larger (1.83 GB, ~2.6 GB RAM) and not recommended for typical use.
What GPU do you need for qwen3 tts 0.6b base?
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 (1.8 GB file, about 2.6 GB in use).
Which qwen3 tts 0.6b base quant should you choose?
Q8_0 (1.0 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 Q4_K at 0.5 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about qwen3 tts 0.6b base
How much VRAM does qwen3 tts 0.6b base need?
About 1.6 GB at Q8_0 with an 8K context window. That is the 1.0 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 qwen3 tts 0.6b base on an 8 GB GPU?
Yes, with the smaller files: the 1.8 GB file needs about 2.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of qwen3 tts 0.6b base GGUF?
It depends on the quant: Q4_K is 0.5 GB, Q8_0 is 1.0 GB, file is 1.8 GB.
Where can I download qwen3 tts 0.6b base GGUF?
The files are on Hugging Face in the cstr/qwen3-tts-0.6b-base-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 qwen3 tts 0.6b base 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 Qwen3‑TTS 0.6B Base on 8 GB VRAM?
The Q8_0 quant requires about 1.6 GB RAM at 8k context, so it can run on 8 GB VRAM with headroom for other processes. The Q4_K quant uses about 1.1 GB RAM, which is even more comfortable.
Do I need a separate tokenizer GGUF?
Yes, the model requires the tokenizer/codec GGUF from cstr/qwen3-tts-tokenizer-12hz-GGUF to function.
Is the model licensed for commercial use?
The model is released under Apache‑2.0, which permits commercial use with attribution.