Ferraronp
/

CosyVoice3-qwen2.5-0.5b-speech-gguf

Model card Files Files and versions

CosyVoice Qwen2.5 0.5B (GGUF)

GGUF conversion of a CosyVoice-style speech token model.

Notes

Outputs speech tokens, not audio
Requires external pipeline

Links

Converter: https://github.com/Ferraronp/CosyVoice-gguf-converter
Works with: https://github.com/Ferraronp/CosyVoice (fork with llama-cpp-python backend)

Downloads last month: 470

GGUF

Model size

0.6B params

Architecture

qwen2

Hardware compatibility

Log In to add your hardware

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

32-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Ferraronp/CosyVoice3-qwen2.5-0.5b-speech-gguf

Base model

FunAudioLLM/Fun-CosyVoice3-0.5B-2512

Quantized

(22)

this model