# Provenance — majentik/Qwen3-ASR-0.6B-MLX-6bit

- Upstream repo: `Qwen/Qwen3-ASR-0.6B-hf`
- Upstream revision: `6aa69c382e2b426eee1f5870d4c95859a74b6445`
- Quantization: bits=6, mode=affine, group_size=64
- Command: `python -m pipelines.mlx_direct_quantize --model qwen3-asr-0.6b --base-dir /private/tmp/mlx-direct-release/qwen3-asr-0.6b/base --out-dir /tmp/mlx-direct-release/qwen3-asr-0.6b/6bit --bits 6 --mode affine --group-size 64`
- Input bytes (BF16 base): 1576380161
- Output bytes (this variant): 868764910
- Toolchain: mlx 0.31.2, huggingface_hub 0.36.2
- Generated: 2026-07-03T14:26:41.314910+00:00

Audio-inference smoke was performed post-upload on 2026-07-03; this variant passed its CER gate — see the README's Audio inference smoke section. General runtime support remains pending upstream mlx-lm support for the `qwen3_asr` audio-text architecture (the Hugging Face runtime requires transformers 5.13+ — `qwen3_asr` merged after the 5.12.1 release).