# LightOnOCR-3-4B vs Baidu Unlimited-OCR-2 (slim)

> LightOnOCR-3-4B scores 61 (C) to Baidu Unlimited-OCR-2's 54.2 (C) for ocr. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/lightonocr-3-4b-vs-unlimited-ocr-2.md (~6,800 tokens) · this version ~730 tokens · JSON https://www.anchorterminal.com/compare/lightonocr-3-4b-vs-unlimited-ocr-2.json · canonical https://www.anchorterminal.com/compare/lightonocr-3-4b-vs-unlimited-ocr-2
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-10
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

LightOnOCR-3-4B scores 61 (C) on agent readiness against Baidu Unlimited-OCR-2's 54.2 (C), and leads in 3 of 4 scored categories. Baidu Unlimited-OCR-2 leads on agent interface. Both do ocr.

- LightOnOCR-3-4B: C 61, rank #73 of 160 open-weight models · https://www.anchorterminal.com/tools/lightonocr-3-4b.min.md
- Baidu Unlimited-OCR-2: C 54.2, rank #133 of 160 open-weight models · https://www.anchorterminal.com/tools/unlimited-ocr-2.min.md
- LightOnOCR-3-4B, good for Agents that need located, labelled document blocks from a model they can use commercially without conditions Ahead on Reach, 70 against 55; Risk, 55 against 45.
- Baidu Unlimited-OCR-2, good for Pipelines with an NVIDIA GPU that need long scanned or rendered documents parsed in one pass, with page order, cross-page tables and boxes kept Ahead on Agent interface, 75 against 70.

| Category | LightOnOCR-3-4B | Baidu Unlimited-OCR-2 |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 70 | 55 |
| Risk (20%) | 55 | 45 |
| Agent interface (10%) | 70 | 75 |
| Documentation and upkeep (10%) | 51 | 50 |

| Fact (where they differ) | LightOnOCR-3-4B | Baidu Unlimited-OCR-2 |
| --- | --- | --- |
| Vendor | LightOn | Baidu |
| Licence | Apache-2.0 | MIT (Hub metadata; the Hugging Face repository has no LICENSE file, and the GitHub code repository's LICENSE is the MIT text, copyright 2026 Baidu) |
| Last release | 2026-10-09 | 2026-10-26 |

Why the edge:
- Reach, LightOnOCR-3-4B +15: LightOnOCR-3-4B 70 (Memory 30, the only build from LightOn is the BF16 safetensors file, 9.08 GB, and 9.08 GB × 1.2 = 10.9 GB, within 16 GB.); Baidu Unlimited-OCR-2 55 (Memory earns the full 30, since the only build is 6.69 GB of BF16 weights that need about 8 GB with the fifth added.)
- Risk, LightOnOCR-3-4B +10: LightOnOCR-3-4B 55 (File safety 25, one safetensors file, no .bin, .pt or .pth files and no Python in the repository.); Baidu Unlimited-OCR-2 45 (File safety gets 15, safetensors only but loaded with trust_remote_code or through a prebuilt SGLang wheel from the repository.)
- Agent interface, Baidu Unlimited-OCR-2 +5: LightOnOCR-3-4B 70 (Chat template 20, chat_template.jinja in the repository (7,759 characters), Qwen 3.5's template with thinking off by default.); Baidu Unlimited-OCR-2 75 (Read for a document parser, the tool-calling, trained tool calling and structured-output lines stand for what it takes and returns.)