Qwen3-ASR-0.6B-8bit is a quantized version of a Qwen-based automatic speech recognition model hosted on Hugging Face. It is designed for efficient local inference using the MLX framework on Apple hardware. The model accepts audio input and produces transcribed text, making it suitable for on-device or offline ASR applications.
Qwen3 ASR 0.6B sits in PulseGate's Foundation models & chat category. It focuses on running efficient automatic speech recognition models locally on Apple silicon hardware. It is built as an open-source project for developers. Qwen3 ASR 0.6B is open source under the Open Source license. It runs on the web, the command line, and API.
Behind Qwen3 ASR 0.6B is mlx-community, and the product first shipped in 2026. It operates in a well-populated space: PulseGate tracks 15 similar tools. Key capabilities include Speech Recognition, 8-bit Quantization, and MLX Optimized.
Latest indexed changes and source events
mlx-community/Qwen3-ASR-0.6B-8bit verified by the PulseGate indexer
Other apps tracked under the same category.