Qwen3-TTS-GGUF is an open-weight model from ExNihilus, released under Apache License 2.0. Its published files total 6.5 GB.
Unmodified copy of selected files from Serveurperso/Qwen3-TTS-GGUF at revision b7ee2e8c7459c3bea99da23e3d178125a7d1713c, kept so that SubVox Pro (Unity editor plugin by ExNihilus) can download a stable, pinned version of the model.
Model Card
By ExNihilus, published under apache-2.0, revision 7a67e407583c.
Unmodified copy of selected files from Serveurperso/Qwen3-TTS-GGUF at revision b7ee2e8c7459c3bea99da23e3d178125a7d1713c, kept so that SubVox Pro (Unity editor plugin by ExNihilus) can download a stable, pinned version of the model. All credit goes to the original authors: the conversion by Serveurperso and the original model Qwen/Qwen3-TTS-12Hz-1.7B-Base. - qwen-talker-1.7b-base-Q80.gguf - qwen-talker-1.7b-customvoice-Q80.gguf - qwen-talker-1.7b-voicedesign-Q80.gguf - qwen-tokenizer-12hz-Q80.gguf
Read ExNihilus's full model card
Qwen3-TTS-GGUF (mirror)
Unmodified copy of selected files from Serveurperso/Qwen3-TTS-GGUF at revision
b7ee2e8c7459c3bea99da23e3d178125a7d1713c, kept so that SubVox Pro (Unity editor plugin by ExNihilus)
can download a stable, pinned version of the model.
All credit goes to the original authors: the conversion by Serveurperso and the original model Qwen/Qwen3-TTS-12Hz-1.7B-Base.
- License: Apache License 2.0, same as the source repository. No file was modified.
- Original model card:
ORIGINAL_README.md
Files
qwen-talker-1.7b-base-Q8_0.ggufqwen-talker-1.7b-customvoice-Q8_0.ggufqwen-talker-1.7b-voicedesign-Q8_0.ggufqwen-tokenizer-12hz-Q8_0.gguf
Identity and Version
- Repository
- ExNihilus/Qwen3-TTS-GGUF
- Publisher
- ExNihilus
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- Not stated by the source
- Languages
- Not stated by the source
- Revision
- 7a67e407583cc7b7a0cf1b522b0f127993a3668d
- First published
- 2026-10-06
- Last updated
- 2026-10-06
Files and Weights
7 files, 6.5 GB in total. The weights are 4 files totalling 6.5 GB in gguf.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| qwen-talker-1.7b-base-Q8_0.gguf | Weights | 2.1 GB | 4b9a33a23690 |
| qwen-talker-1.7b-customvoice-Q8_0.gguf | Weights | 2.0 GB | cab2cff67a0a |
| qwen-talker-1.7b-voicedesign-Q8_0.gguf | Weights | 2.0 GB | 575610ab1ddc |
| qwen-tokenizer-12hz-Q8_0.gguf | Weights | 291.2 MB | 1883beeed993 |
| ORIGINAL_README.md | Documentation | 4.9 KB | — |
| README.md | Documentation | 1.1 KB | — |
| .gitattributes | Repository | 1.8 KB | — |
License and Download
- License
- apache-2.0
- Access
- Open weights, no gate
- Download size
- 6.5 GB
Released by ExNihilus through its official repository on Hugging Face. Read the license.
Built From
- Derived from Qwen/Qwen3-TTS-12Hz-1.7B-Base
- Quantized from Qwen/Qwen3-TTS-12Hz-1.7B-Base
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 6.5 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About Qwen3-TTS-GGUF
Can I use Qwen3-TTS-GGUF commercially?
Yes. Qwen3-TTS-GGUF is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.