Qwen3-ASR-0.6B-gguf is a compact 0.6B parameter automatic speech recognition model provided in multiple GGUF quantized formats. It allows local audio transcription and speech processing using standard GGUF inference tools. The model targets developers building offline or on-device voice applications that require low memory and compute resources.
In the Speech to text space, Qwen3 ASR 0.6B takes a focused approach. It focuses on running lightweight speech-to-text models locally with minimal resource usage. It is built as an open-source project for developers. Qwen3 ASR 0.6B is open source under the MIT license. It ships for the web, the command line, and API.
Behind Qwen3 ASR 0.6B is handy-computer, and it first shipped in 2026. The project is developed in the open on GitHub with 858 stars and 423 commits in the last 90 days. It operates in a well-populated space: PulseGate tracks 12 similar projects. Key capabilities include automatic speech recognition, Quantized GGUF, and audio processing.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do