# LFM3-1.7B vs Baidu Unlimited-OCR-2 (slim)

> LFM3-1.7B scores 61 (C) to Baidu Unlimited-OCR-2's 54.2 (C) for open-weight models you run yourself. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/lfm3-1-7b-vs-unlimited-ocr-2.md (~10,100 tokens) · this version ~830 tokens · JSON https://www.anchorterminal.com/compare/lfm3-1-7b-vs-unlimited-ocr-2.json · canonical https://www.anchorterminal.com/compare/lfm3-1-7b-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)

LFM3-1.7B 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 risk. Both do open-weight models you run yourself.

- LFM3-1.7B: C 61, rank #69 of 160 open-weight models · https://www.anchorterminal.com/tools/lfm3-1-7b.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
- LFM3-1.7B, good for Agents on a laptop, phone or small server that need tool calling and a long context from a model under 2 GB at 4 bits Ahead on Reach, 85 against 55; Agent interface, 100 against 75; Documentation and upkeep, 67 against 50.
- 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 Risk, 45 against 40.

| Category | LFM3-1.7B | Baidu Unlimited-OCR-2 |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 85 | 55 |
| Risk (20%) | 40 | 45 |
| Agent interface (10%) | 100 | 75 |
| Documentation and upkeep (10%) | 67 | 50 |

| Fact (where they differ) | LFM3-1.7B | Baidu Unlimited-OCR-2 |
| --- | --- | --- |
| Vendor | Liquid AI | Baidu |
| Licence | LFM Open License v1.0 (free commercial use below $10M annual revenue) | 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) |
| llms.txt | yes | no |
| Last release | 2026-11-09 | 2026-10-26 |

Why the edge:
- Reach, LFM3-1.7B +30: LFM3-1.7B 85 (Memory 30, Liquid's Q4_K_M GGUF is 1.10 GB, and 1.10 GB × 1.2 = 1.3 GB, which fits 8 GB, well inside the 16 GB line.); 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.)
- Agent interface, LFM3-1.7B +25: LFM3-1.7B 100 (Chat template 20, chat_template.jinja in the repository (12,129 characters), with roles, tools, deferred tools, tool results and the thinking switch.); 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.)
- Documentation and upkeep, LFM3-1.7B +17: LFM3-1.7B 67 (Model card 17, Intended use (local agents, tool calling, structured outputs, fine-tuning), a limitation (not recommended for agentic coding or complex multi-ste…); Baidu Unlimited-OCR-2 50 (The card covers intended use and the new attention, and misses limitations, parameters, context length, languages and a cut-off (5).)
- Risk, Baidu Unlimited-OCR-2 +5: LFM3-1.7B 40 (File safety 15, safetensors only, no .bin, .pt or .pth files (25).); 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.)