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

> LightOnOCR-3-4B scores 61 (C) to Chandra OCR 2's 54.7 (C) for ocr. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/chandra-ocr-2-vs-lightonocr-3-4b.md (~3,200 tokens) · this version ~680 tokens · JSON https://www.anchorterminal.com/compare/chandra-ocr-2-vs-lightonocr-3-4b.json · canonical https://www.anchorterminal.com/compare/chandra-ocr-2-vs-lightonocr-3-4b
- 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 Chandra OCR 2's 54.7 (C), and leads in 3 of 4 scored categories. Both do ocr.

- Chandra OCR 2: C 54.7, rank #127 of 160 open-weight models · https://www.anchorterminal.com/tools/chandra-ocr-2.min.md
- LightOnOCR-3-4B: C 61, rank #73 of 160 open-weight models · https://www.anchorterminal.com/tools/lightonocr-3-4b.min.md
- Chandra OCR 2, good for Small companies and researchers who need accurate document parsing on their own GPU and fit the licence
- 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 65; Risk, 55 against 45; Documentation and upkeep, 51 against 33.

| Category | Chandra OCR 2 | LightOnOCR-3-4B |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 65 | 70 |
| Risk (20%) | 45 | 55 |
| Agent interface (10%) | 70 | 70 |
| Documentation and upkeep (10%) | 33 | 51 |

| Fact (where they differ) | Chandra OCR 2 | LightOnOCR-3-4B |
| --- | --- | --- |
| Vendor | Endless Labs, Inc. (Datalab) | LightOn |
| Licence | Modified OpenRAIL-M (free for research, personal use and companies under $2M in revenue and funding) | Apache-2.0 |
| Last release | 2026-06-26 | 2026-10-09 |
| Terms last updated | not read yet | no document linked |

Why the edge:
- Documentation and upkeep, LightOnOCR-3-4B +18: Chandra OCR 2 33 (Model card 8, Intended use and the languages (over 90) are on the card.); LightOnOCR-3-4B 51 (Model card 11, Intended use, a limitation (instructions other than its two prompts are out of distribution), the architecture (Qwen 3.5's) and the size (4B) are…)
- Risk, LightOnOCR-3-4B +10: Chandra OCR 2 45 (File safety 25, one safetensors file, no .bin, .pt or .pth files and no Python in the model repository.); LightOnOCR-3-4B 55 (File safety 25, one safetensors file, no .bin, .pt or .pth files and no Python in the repository.)
- Reach, LightOnOCR-3-4B +5: Chandra OCR 2 65 (Memory 30, the only build from Datalab is the BF16 safetensors file, 10.59 GB, and 10.59 GB × 1.2 = 12.7 GB, within 16 GB.); 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.)