# DeepSeek-OCR 2 vs Xiaomi-OCR-0 (slim)

> Xiaomi-OCR-0 scores 59 (C) to DeepSeek-OCR 2's 49.2 (D) for ocr. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/deepseek-ocr-2-vs-xiaomi-ocr-0.md (~3,800 tokens) · this version ~730 tokens · JSON https://www.anchorterminal.com/compare/deepseek-ocr-2-vs-xiaomi-ocr-0.json · canonical https://www.anchorterminal.com/compare/deepseek-ocr-2-vs-xiaomi-ocr-0
- 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)

Xiaomi-OCR-0 scores 59 (C) on agent readiness against DeepSeek-OCR 2's 49.2 (D), and leads in every scored category. Both do ocr.

- DeepSeek-OCR 2: D 49.2, rank #147 of 160 open-weight models · https://www.anchorterminal.com/tools/deepseek-ocr-2.min.md
- Xiaomi-OCR-0: C 59, rank #101 of 160 open-weight models · https://www.anchorterminal.com/tools/xiaomi-ocr-0.min.md
- DeepSeek-OCR 2, good for Teams that want an Apache 2.0 OCR model on a small GPU and already run vLLM
- Xiaomi-OCR-0, good for Agents and pipelines on modest hardware that need local OCR of scanned or photographed pages, receipts and forms into Markdown or JSON Ahead on Reach, 80 against 65; Risk, 65 against 50; Agent interface, 70 against 35; Documentation and upkeep, 65 against 22.

| Category | DeepSeek-OCR 2 | Xiaomi-OCR-0 |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 65 | 80 |
| Risk (20%) | 50 | 65 |
| Agent interface (10%) | 35 | 70 |
| Documentation and upkeep (10%) | 22 | 65 |

| Fact (where they differ) | DeepSeek-OCR 2 | Xiaomi-OCR-0 |
| --- | --- | --- |
| Vendor | DeepSeek | Xiaomi |
| Licence | Apache-2.0 | Apache-2.0 (card metadata and card text; the Hugging Face repository has no LICENSE file, and the GitHub code repository's LICENSE is the Apache 2.0 text, copyright 2026 Xiaomi Corporation) |
| Last release | 2026-02-03 | 2026-09-29 |

Why the edge:
- Documentation and upkeep, Xiaomi-OCR-0 +43: DeepSeek-OCR 2 22 (Model card 2, Intended use is there, as the two prompts.); Xiaomi-OCR-0 65 (The card covers intended use and parameters and misses limitations, architecture, context length, languages and a cut-off (5).)
- Agent interface, Xiaomi-OCR-0 +35: DeepSeek-OCR 2 35 (Chat template 10, no Jinja template in the repository and none in tokenizer_config.json.); Xiaomi-OCR-0 70 (Read for a document parser, the tool-calling, trained tool calling and structured-output lines stand for what it takes and returns.)
- Reach, Xiaomi-OCR-0 +15: DeepSeek-OCR 2 65 (Memory 30, the only build from DeepSeek is the BF16 safetensors file, 6.78 GB, and 6.78 GB × 1.2 = 8.1 GB, within 16 GB.); Xiaomi-OCR-0 80 (Memory earns the full 30, since the only build is a 1.75 GB BF16 file that needs about 2.1 GB with the fifth added.)
- Risk, Xiaomi-OCR-0 +15: DeepSeek-OCR 2 50 (File safety 15, safetensors only, no .bin, .pt or .pth files (25), less 10 because the card's documented way to load it is trust_remote_code, which runs the rep…); Xiaomi-OCR-0 65 (File safety gets 25, one safetensors file with no Python in the repository and native loading everywhere.)