badlogicgames/qwen3-tts-0.6b-q8_0-gguf

Qwen3-TTS 0.6B Q8_0 GGUF

Locally converted GGUF files for use with `qwen3-tts.cpp`.

Files

• —qwen3-tts-0.6b-q8_0.gguf — Qwen3-TTS 12Hz 0.6B base model converted from Qwen/Qwen3-TTS-12Hz-0.6B-Base and quantized to GGML Q8_0.
• —qwen3-tts-tokenizer-f16.gguf — tokenizer/vocoder GGUF converted from Qwen/Qwen3-TTS-Tokenizer-12Hz in F16.

Notes

This is a runtime artifact for the GGML/C++ implementation. It is not an official Qwen release.