Qwen3 Tts GGUF
No Tag : means that the model belongs to the base model family CustomVoice : means that the model belongs to the CustomVoice model family VoiceDesign : means that the model belongs to the VoiceDesign model family
Source du modèle
- Type
- Other
- Taille du fichier
- 335 MB–7,19 GB
- Version
- vRevision 19e3edc
- Mis à jour
- 25 sept. 2026
- Téléchargements
- 34
- Source
- Hugging Face
Description de la source
These models will NOT work with most libraries or inference engines that accept GGUF models.
model tags :
Model families :
No Tag : means that the model belongs to the base model family CustomVoice : means that the model belongs to the CustomVoice model family VoiceDesign : means that the model belongs to the VoiceDesign model family
Model Parameters :
0.6b : means that the model has 0.6 billion parameters 1.7b : means that the model has 1.7 billion parameters
Model Quantization :
f16 : means that the model has no quantization applied to it ( full precision ) q8_0 : means that the model has been quantized to 8 bits.
NOTE : FP32 IS an option ( f32 ) but is not recommended , if you want the highest quality output possible f16 is literally just as good.
Sources
1 source
Sources
1 sourceVérifié 6 sept.
Download files
Artefacts du modèle
20 artefacts
Artefacts du modèle
20 artefactsqwen3-tts-0.6b-customvoice-f16.gguf
gguf · 1,69 GB · SHA-256 b89d5e1c5acb…774d · Hugging Face
Download fileqwen3-tts-0.6b-customvoice-f32.gguf
gguf · 3,38 GB · SHA-256 f2415c0847c0…7705 · Hugging Face
Download fileqwen3-tts-0.6b-customvoice-q8_0.gguf
gguf · 1,23 GB · SHA-256 4900799491c8…e559 · Hugging Face
Download fileqwen3-tts-1.7b-customvoice-f16.gguf
gguf · 3,58 GB · SHA-256 0f7b3374ec47…f88e · Hugging Face
Download fileqwen3-tts-1.7b-customvoice-f32.gguf
gguf · 7,15 GB · SHA-256 acdaad765336…766f · Hugging Face
Download fileqwen3-tts-1.7b-customvoice-q8_0.gguf
gguf · 2,27 GB · SHA-256 d57b066c0abc…3c96 · Hugging Face
Download fileqwen3-tts-1.7b-voicedesign-f16.gguf
gguf · 3,58 GB · SHA-256 bfdd3eea89eb…7fcb · Hugging Face
Download fileqwen3-tts-1.7b-voicedesign-f32.gguf
gguf · 7,15 GB · SHA-256 0dfcb17b9b1d…f4ea · Hugging Face
Download fileqwen3-tts-1.7b-voicedesign-q8_0.gguf
gguf · 2,27 GB · SHA-256 7bedeb4d4e2a…55cc · Hugging Face
Download fileqwen3-tts-tokenizer-f16-f16.gguf
gguf · 357 MB · SHA-256 37965961f12a…8e96 · Hugging Face
Download fileqwen3-tts-tokenizer-f16-f32.gguf
gguf · 432 MB · SHA-256 251363c2b816…3a19 · Hugging Face
Download fileqwen3-tts-tokenizer-f16-q8_0.gguf
gguf · 335 MB · SHA-256 06d3e4ecfeed…c55a · Hugging Face
Download fileqwen3-tts-tokenizer-f32-f16.gguf
gguf · 575 MB · SHA-256 50e0e2f0db05…408e · Hugging Face
Download fileqwen3-tts-tokenizer-f32-f32.gguf
gguf · 650 MB · SHA-256 673d935ff7fe…d58d · Hugging Face
Download fileExtraits de sources
2 extraits
Extraits de sources
2 extraits--- license: apache-2.0 pipeline_tag: text-to-speech --- ## These models will **NOT** work with most libraries or inference engines that accept GGUF models. # **model tags :** # Model families : **No Tag :** means that the model belongs to the *base* model family **CustomVoice :** means that the model belongs to the *CustomVoice* model family **VoiceDesign :** means that the model belongs to the *VoiceDesign* model family # Model Parameters : **0.6b :** means that the model has 0.6 billion parameters **1.7b :** means that the model has 1.7 billion parameters # Model Quantization : **f16 :** means that the model has no quantization applied to it ( full precision ) **q8_0 :** means that the model has been quantized to 8 bits. ## NOTE : FP32 IS an option ( f32 ) but is not recommended , if you want the highest quality output possible f16 is literally just as good.
Source context: 34 downloads · 0 likes · Pipeline text-to-speech · Repo librellama/qwen3-tts-GGUF
