librellama/qwen3-tts-GGUF

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.