{
  "id": 16961519,
  "title": "Unlimited-OCR 2 on a 16 GB GPU: it reads as well as Chandra 2, but it is not unlimited",
  "url": "https://urgent.news/2026/10/28/unlimited-ocr-2-on-a-16-gb-gpu-it-reads-as-well-as-chandra-2-but-it",
  "topic": "tech",
  "section": "Tech",
  "published": "2026-10-28T21:34:13.000Z",
  "source": {
    "name": "Dev.to",
    "slug": "dev-to",
    "url": "https://dev.to/efraingaray/unlimited-ocr-2-on-a-16-gb-gpu-it-reads-as-well-as-chandra-2-but-it-is-not-unlimited-34bb"
  },
  "original_language": "en",
  "account": "On October 27, Baidu unveiled Unlimited-OCR 2, a 3.3 billion parameter model released under the MIT license. Its claim was that its sparse attention mechanism maintained nearly constant per-step decoding latency and memory footprint, regardless of document length. To test this claim, a comparison was made between Unlimited-OCR 2, Chandra 2, Tesseract, Marker 2.0, and DeepSeek-OCR, using PDFs of real Central Bank of Chile reports. The median character error rate per page for Unlimited-OCR 2 was 0.12%, which was on par with Chandra 2 and superior to Tesseract, Marker, and DeepSeek-OCR. However, when running on a 16 GB GPU, Unlimited-OCR 2 struggled as the document size increased. With more pages in one request, memory usage rose, and time per token increased. The transformers path, which kept every token in a dynamic cache, was faster than the transformers, but the 10-page window mode had issues. For large files, Marker proved to be the practical choice, completing a 74-page report in 12.6 minutes using 4.2 GB of the GPU. Chandra 2 took 46 minutes and 11 GB of GPU memory. Unlimited-OCR 2 is MIT-licensed, while Chandra 2's weights are only available under specific funding conditions. The post also covered installation difficulties on NixOS and potential threats to validity, with full measurements, pre-registered sheet, and scripts available at https://efraingaray.com/en/blog/unlimited-ocr-2-16gb/.",
  "summary": "On October 27 Baidu released Unlimited-OCR 2: 3.3B parameters, MIT license, and a promise that its sparse attention keeps \"per-step decoding latency and memory footprint nearly constant regardless of document length\". That night I ran it on a 16 GB RTX 4070 Ti SUPER against what I actually used for huge PDFs (Datalab's Marker and Chandra 2, locally), DeepSeek-OCR, Unlimited-OCR 1 and Tesseract,…",
  "key_points": [
    "Unlimited-OCR 2 model matches Chandra 2's performance on error rates",
    "Struggles with memory and time on 16 GB GPU for large documents",
    "Marker 2.0 recommended for practical large-file OCR processing"
  ],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}