VyvoTTS-v0-Qwen3-0.6B-GGUF

VyvoTTS-v0-Qwen3-0.6B is an English Text-to-Speech (TTS) model built on the Qwen3-0.6B architecture and trained using a 10,000-hour dataset to produce natural-sounding speech. With approximately 810 million parameters and licensed under MIT, the model offers flexible usage as a pretrained base for further development, especially recommended to be enhanced by leveraging the Emilia dataset and fine-tuning for single-speaker scenarios. Users can integrate VyvoTTS with the unsloth and SNAC frameworks for speech generation, and the model supports sequence lengths up to 8,192 tokens. Although it currently exhibits a high Word Error Rate (WER), its open-source nature and compatibility with popular Python libraries make it an accessible starting point for advanced speech synthesis projects.

Model Files

File Name	Size	Quant Type
VyvoTTS-v0-Qwen3-0.6B.BF16.gguf	1.26 GB	BF16
VyvoTTS-v0-Qwen3-0.6B.F16.gguf	1.26 GB	F16
VyvoTTS-v0-Qwen3-0.6B.F32.gguf	2.51 GB	F32
VyvoTTS-v0-Qwen3-0.6B.Q2_K.gguf	321 MB	Q2_K
VyvoTTS-v0-Qwen3-0.6B.Q3_K_L.gguf	393 MB	Q3_K_L
VyvoTTS-v0-Qwen3-0.6B.Q3_K_M.gguf	372 MB	Q3_K_M
VyvoTTS-v0-Qwen3-0.6B.Q3_K_S.gguf	348 MB	Q3_K_S
VyvoTTS-v0-Qwen3-0.6B.Q4_0.gguf	406 MB	Q4_0
VyvoTTS-v0-Qwen3-0.6B.Q4_1.gguf	434 MB	Q4_1
VyvoTTS-v0-Qwen3-0.6B.Q4_K.gguf	421 MB	Q4_K
VyvoTTS-v0-Qwen3-0.6B.Q4_K_M.gguf	421 MB	Q4_K_M
VyvoTTS-v0-Qwen3-0.6B.Q4_K_S.gguf	408 MB	Q4_K_S
VyvoTTS-v0-Qwen3-0.6B.Q5_0.gguf	461 MB	Q5_0
VyvoTTS-v0-Qwen3-0.6B.Q5_1.gguf	489 MB	Q5_1
VyvoTTS-v0-Qwen3-0.6B.Q5_K.gguf	469 MB	Q5_K
VyvoTTS-v0-Qwen3-0.6B.Q5_K_M.gguf	469 MB	Q5_K_M
VyvoTTS-v0-Qwen3-0.6B.Q5_K_S.gguf	461 MB	Q5_K_S
VyvoTTS-v0-Qwen3-0.6B.Q6_K.gguf	520 MB	Q6_K
VyvoTTS-v0-Qwen3-0.6B.Q8_0.gguf	671 MB	Q8_0

Quants Usage

(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)

Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):