Qwen3 TTS 12Hz 0.6B CustomVoice needs about 1.8 GB of memory at Q4_K_M (a 0.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 22 quants, from 0.3 GB (Q2_K) to 2.4 GB (F32). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.
Qwen3 TTS 12Hz 0.6B CustomVoice – 10‑language text‑to‑speech with 9 built‑in voices
Qwen3 TTS 12Hz 0.6B CustomVoice is a multilingual text‑to‑speech model supporting Chinese, English, Japanese, Korean, German, French, Russian, Portuguese, Spanish, and Italian. It offers fine‑grained style control via natural language instructions and streams audio with low latency.
Good at
- Multilingual synthesis
- Fine‑grained style control
- Low‑latency streaming
Limits
- No vision support
- Requires one model file and one codec file
- License: apache‑2.0
Best for
- Developing multilingual TTS apps
- Creating voice‑controlled assistants
- Generating audio content for multiple languages
Who it’s for. Engineers and developers building offline or low‑latency text‑to‑speech solutions that need multiple languages and customizable voice styles. The model runs on CPU or GPU (CUDA, Vulkan, Metal) via llama.cpp and codec.cpp.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 0.3 GB | 1.7 GB | Fits | Get file → | |
| Q3_K_S | 0.3 GB | 1.8 GB | Fits | Get file → | |
| Q3_K_M | 0.3 GB | 1.8 GB | Fits | Get file → | |
| Q3_K_L | 0.4 GB | 1.8 GB | Fits | Get file → | |
| Q4_0 | 0.4 GB | 1.8 GB | Fits | Get file → | |
| Q4_K_S | 0.4 GB | 1.8 GB | Fits | Get file → | |
| Q4_K_M | 0.4 GB | 1.8 GB | Fits | Get file → | |
| Q4_1 | 0.4 GB | 1.8 GB | Fits | Get file → | |
| Q5_0 | 0.4 GB | 1.9 GB | Fits | Get file → | |
| Q5_K_S | 0.4 GB | 1.9 GB | Fits | Get file → | |
| Q5_K_M | 0.4 GB | 1.9 GB | Fits | Get file → | |
| Q5_1 | 0.5 GB | 1.9 GB | Fits | Get file → | |
| Q6_K | 0.5 GB | 1.9 GB | Fits | Get file → | |
| Q8_0 | 0.6 GB | 2.1 GB | Fits | Get file → | |
| BF16 | 1.2 GB | 2.6 GB | Fits | Get file → | |
| F16 | 1.2 GB | 2.6 GB | Fits | Get file → | |
| Q4_K_M | 1.3 GB | 2.7 GB | Fits | Get file → | |
| Q5_K_M | 1.3 GB | 2.7 GB | Fits | Get file → | |
| Q8_0 | 1.3 GB | 2.8 GB | Fits | Get file → | |
| F16 | 1.4 GB | 2.8 GB | Fits | Get file → | |
| F32 | 1.7 GB | 3.1 GB | Fits | Get file → | |
| F32 | 2.4 GB | 3.8 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K (0.38 GB) or Q5_0 (0.44 GB). For 16 GB VRAM, Q8_0 (0.64 GB) or BF16 (1.2 GB) provide higher quality. Larger models like F32 (1.68 GB) need 32 GB VRAM or more.
What GPU do you need for Qwen3 TTS 12Hz 0.6B CustomVoice?
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 F32 (2.4 GB file, about 3.8 GB in use).
Which Qwen3 TTS 12Hz 0.6B CustomVoice quant should you choose?
Q4_K_M is the usual starting point for Qwen3 TTS 12Hz 0.6B CustomVoice: it balances file size and quality well. Here it is a 0.4 GB file.
The Q8_0 file is 0.6 GB, about 1.6 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 0.3 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 Qwen3 TTS 12Hz 0.6B CustomVoice
How much VRAM does Qwen3 TTS 12Hz 0.6B CustomVoice need?
About 1.8 GB at Q4_K_M with an 8K context window. That is the 0.4 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 12Hz 0.6B CustomVoice on an 8 GB GPU?
Yes, with F32: the 2.4 GB file needs about 3.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Qwen3 TTS 12Hz 0.6B CustomVoice GGUF?
It depends on the quant: Q2_K is 0.3 GB, Q3_K_S is 0.3 GB, Q3_K_M is 0.3 GB, Q3_K_L is 0.4 GB, Q4_0 is 0.4 GB, Q4_K_S is 0.4 GB and 16 more.
What context length does Qwen3 TTS 12Hz 0.6B CustomVoice support?
The GGUF header lists a trained context length of 32,768 tokens (32K). 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 Qwen3 TTS 12Hz 0.6B CustomVoice GGUF?
The files are on Hugging Face in the BricksDisplay/Qwen3-TTS-12Hz-0.6B-CustomVoice-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 12Hz 0.6B CustomVoice 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 on 8 GB VRAM?
Yes, the Q4_K quantization requires about 1.8 GB memory at 8k context, which fits in 8 GB VRAM.
Does the model support voice cloning?
No, voice cloning is not available in the 0.6B CustomVoice variant.
What languages are supported?
Chinese, English, Japanese, Korean, German, French, Russian, Portuguese, Spanish, and Italian.