You can deploy this model and start earning money today!

Six666/
mlx-qwen3-asr-0.6b-8bit

Name: mlx-qwen3-asr-0.6b-8bit
Availability: InStock

Views

No views yet

Six666/mlx-qwen3-asr-0.6b-8bit

8-bit MLX-quantized conversion of Qwen/Qwen3-ASR-0.6B, for use with the mlx-qwen3-asr package on Apple Silicon.

bits: 8
group_size: 64
dtype (pre-quant): float16
quantization: MLX affine group quantization (nn.quantize)

Usage

python

from mlx_qwen3_asr import transcribe
result = transcribe("audio.wav", model="Six666/mlx-qwen3-asr-0.6b-8bit")
print(result.text)

mlx-qwen3-asr audio.wav --model Six666/mlx-qwen3-asr-0.6b-8bit

Note: produced with mlx-qwen3-asr's own converter. The mlx-community/Qwen3-ASR-* quantized repos use mlx-audio's layer naming and will not load with this package.