Qwen3-TTS-Tokenizer-12Hz needs about 0.8 GB of memory at Q4_K_M (a 0.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 24 quants, from 0.3 GB (Q4_K_M) to 7.7 GB (F32).
Qwen3-TTS-Tokenizer-12Hz: 0.915B multilingual TTS tokenizer
Qwen3-TTS-Tokenizer-12Hz is a 0.915B parameter tokenizer for 12 Hz text‑to‑speech. It compresses speech into high‑dimensional codes for efficient synthesis. The model is released under Apache‑2.0 and supports multiple languages via a discrete multi‑codebook architecture.
Good at
- Efficient acoustic compression
- High‑dimensional semantic modeling
- Low‑latency streaming generation
Limits
- No vision support
- Requires separate talker model
- Large VRAM for higher quant
- No explicit language list provided
Best for
- Voice cloning with 3‑second samples
- Real‑time TTS in interactive apps
- Multilingual TTS pipelines
Who it’s for. Developers building TTS systems that need a lightweight tokenizer. Researchers exploring discrete acoustic representations. Teams integrating Qwen3‑TTS into larger pipelines.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 0.3 GB | 0.8 GB | Fits | Get file → | |
| Q8_0 | 0.3 GB | 0.8 GB | Fits | Get file → | |
| BF16 | 0.4 GB | 0.9 GB | Fits | Get file → | |
| Q4_K_M | 0.6 GB | 1.2 GB | Fits | Get file → | |
| Q4_K_M | 0.6 GB | 1.2 GB | Fits | Get file → | |
| F32 | 0.6 GB | 1.2 GB | Fits | Get file → | |
| Q8_0 | 1.0 GB | 1.6 GB | Fits | Get file → | |
| Q8_0 | 1.0 GB | 1.6 GB | Fits | Get file → | |
| Q4_K_M | 1.2 GB | 1.8 GB | Fits | Get file → | |
| Q4_K_M | 1.2 GB | 1.8 GB | Fits | Get file → | |
| Q4_K_M | 1.2 GB | 1.9 GB | Fits | Get file → | |
| BF16 | 1.8 GB | 2.5 GB | Fits | Get file → | |
| BF16 | 1.8 GB | 2.6 GB | Fits | Get file → | |
| Q8_0 | 2.0 GB | 2.8 GB | Fits | Get file → | |
| Q8_0 | 2.0 GB | 2.8 GB | Fits | Get file → | |
| Q8_0 | 2.1 GB | 2.8 GB | Fits | Get file → | |
| F32 | 3.6 GB | 4.6 GB | Fits | Get file → | |
| F32 | 3.7 GB | 4.6 GB | Fits | Get file → | |
| BF16 | 3.8 GB | 4.8 GB | Fits | Get file → | |
| BF16 | 3.8 GB | 4.8 GB | Fits | Get file → | |
| BF16 | 3.9 GB | 4.8 GB | Fits | Get file → | |
| F32 | 7.7 GB | 9.1 GB | Too big | Get file → | |
| F32 | 7.7 GB | 9.1 GB | Too big | Get file → | |
| F32 | 7.7 GB | 9.1 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (0.25 GB) or Q8_0 (0.29 GB) – both estimate 0.8 GB memory at 8k context. For 16 GB VRAM, Q4_K_M (0.6 GB) or Q8_0 (0.97 GB) are suitable, estimating 1.2–1.6 GB. For 32 GB VRAM, higher precision options like BF16 (1.82 GB) or F32 (3.63 GB) can be used, estimating 2.5–4.6 GB.
What GPU do you need for Qwen3-TTS-Tokenizer-12Hz?
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 Q8_0 (2.1 GB file, about 2.8 GB in use).
- 6 GB VRAM: the best quant that fits is BF16 (3.9 GB file, about 4.8 GB in use).
- 8 GB VRAM: the best quant that fits is BF16 (3.9 GB file, about 4.8 GB in use).
- 12 GB VRAM: the best quant that fits is F32 (7.7 GB file, about 9.1 GB in use).
Which Qwen3-TTS-Tokenizer-12Hz quant should you choose?
Q4_K_M is the usual starting point for Qwen3-TTS-Tokenizer-12Hz: it balances file size and quality well. Here it is a 0.3 GB file.
The Q8_0 file is 0.3 GB, about 1.1 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Qwen3-TTS-Tokenizer-12Hz
How much VRAM does Qwen3-TTS-Tokenizer-12Hz need?
About 0.8 GB at Q4_K_M with an 8K context window. That is the 0.3 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-Tokenizer-12Hz on an 8 GB GPU?
Yes, with BF16: the 3.9 GB file needs about 4.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Qwen3-TTS-Tokenizer-12Hz GGUF?
It depends on the quant: Q4_K_M is 0.3 GB, Q8_0 is 0.3 GB, BF16 is 0.4 GB, Q4_K_M is 0.6 GB, Q4_K_M is 0.6 GB, F32 is 0.6 GB and 18 more.
Where can I download Qwen3-TTS-Tokenizer-12Hz GGUF?
The files are on Hugging Face in the CC-TM/Qwen3-TTS-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-Tokenizer-12Hz 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‑Tokenizer‑12Hz on 8 GB VRAM?
Yes, the Q4_K_M or Q8_0 quantizations are 0.25–0.29 GB and estimate 0.8 GB memory at 8k context.
Does this tokenizer support voice cloning?
It provides the discrete codes needed for voice cloning but requires a separate talker model for synthesis.
What license applies to this model?
The tokenizer is released under Apache‑2.0, matching the parent Qwen3‑TTS model.