PaddleOCR-VL-1.6-MLX-16bit / preprocessor_config.json

Commit History

  1. preprocessor_config.json: preprocessor/processor config: raise vision max_pixels 1,003,520 -> 4,064,256 (6x6 stage of the 28px/token grid: 5,184 merged-token budget; A4 lands ~5,100; min_pixels unchanged 112,896). Small-text OCR tuning for the zoom-4.0 render lane; lower stages selectable client-side via render scale / crop pixel budget. Deliberate divergence from upstream PaddlePaddle/PaddleOCR-VL-1.6 and mlx-community 1.5/1.6 defaults (1,003,520). Measured on M-series: full-page wall ~5x vs 1.0MP cap, crop lane unaffected, server RSS ~2.2 GB.

    Verified signature
    ff95470
  2. MLX 16-bit (bfloat16) conversion of PaddlePaddle/PaddleOCR-VL-1.6 via mlx_vlm convert

    Verified signature
    b854922