Qwen3-ASR 0.6B (GGUF)

Qwen3-ASR-0.6B-Q8_0.gguf: Qwen3-ASR 0.6B by Qwen (Alibaba Cloud), converted to GGUF for transcribe.cpp, for Herald, private offline dictation.

This file is a byte-for-byte copy of the one published at handy-computer/Qwen3-ASR-0.6B-gguf (commit e4e1659); the weights were not changed. Herald downloads it from here, so it doesn't depend on another project's hosting. The other quantisations are at the original repository.

All credit for the model belongs to Qwen (Alibaba Cloud), and for the conversion to the transcribe.cpp authors.