mlx-community/Ming-3.0-audio-tiny-4bit

Ming-3.0 Audio Tiny for MLX

Converted from inclusionAI/Ming-3.0-audio-tiny.

English and Chinese audio understanding, transcription, text chat and spoken dialogue. task='spoken_dialogue' loads the bundled Talker lazily and produces 44.1 kHz audio. Only the thinker language backbone and text head are quantized; audio modules, routers and Talker remain floating-point. Speculative MTP decoding and streaming are not implemented. Reference speaker extraction uses the bundled native MLX CAMPPlus encoder. No ONNX packages are required.

from mlx_audio.sts import load
model = load('dev/ming3/converted/Ming-3.0-audio-tiny-4bit', strict=True)
result = model.generate("speech.wav", task="audio_understanding",
                        text="Describe what you hear.")
print(result.text)

Offline inference on Apple Silicon using native MLX code. The tokenizer is loaded without executing remote code.