Show HN: Unlimited-OCR-2 on Dual-Panel Lab Tables: What Works, What Breaks, How Baidu released Unlimited-OCR-2, a small open-weights document vision-language model, on Hugging Face and ModelScope, and a local test on Apple Silicon found it handled a dense Chinese hospital CBC plus 5-part differential sheet well outside the results grid but merged the page's two side-by-side result lists into a single HTML table. Running in Transformers on MPS after patching two .cuda() calls in masked_scatter_ and forcing image tensors to fp32, the model loaded in about 19 seconds and processed one dense page in about 9 minutes on an M4-class Mac. The tester's fix was to crop the table bounding box at the vertical middle and run each pane through the same model with the built-in "Free OCR." prompt. Baidu released Unlimited-OCR-2 https://huggingface.co/baidu/Unlimited-OCR-2 as open weights also on ModelScope https://modelscope.cn/models/PaddlePaddle/Unlimited-OCR-2 . It is a small document vision-language model https://zlu.me/ai-glossary/vision-language-model/ . It reads pages and returns text with layout tags, reading order, tables, and multi-page context. The model card describes Sparse Reference Sliding Window Attention SR-SWA , which keeps long-document decoding cost from growing as fast as plain full attention. I ran Unlimited-OCR-2 locally on Apple Silicon MPS, fp32 . The PDF stayed on my machine. The test page was a Chinese hospital CBC https://zlu.me/med-glossary/全血细胞计数/ complete blood count + 5-part differential sheet: one page, dense header, then a results grid. Below I describe the layout only. No patient identifiers and no real lab values from that file. What worked without extra code On that page, full-page inference https://zlu.me/ai-glossary/inference/ was already useful for everything outside the results grid: - hospital title Chinese and English - section labels name, sex, age, specimen type, department, order item - timestamps and footer notes - a table ... block with a page-normalized bounding box Runtime on an M4-class Mac: model load about 19 s, one dense page about 9 minutes in Transformers on MPS. The official docs assume NVIDIA CUDA. On Mac I patched two .cuda calls in masked scatter and forced image tensors to fp32 bf16 on MPS drifted . After that, local runs worked. The output is not only a flat string. It returns text blocks, titles, an HTML