# Hy-Memory-30B-A3B vs Baidu Unlimited-OCR-2 (slim)

> Hy-Memory-30B-A3B 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/hy-memory-30b-a3b-vs-unlimited-ocr-2.md (~10,400 tokens) · this version ~830 tokens · JSON https://www.anchorterminal.com/compare/hy-memory-30b-a3b-vs-unlimited-ocr-2.json · canonical https://www.anchorterminal.com/compare/hy-memory-30b-a3b-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)

Hy-Memory-30B-A3B 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 open-weight models you run yourself.

- Hy-Memory-30B-A3B: C 61, rank #68 of 160 open-weight models · https://www.anchorterminal.com/tools/hy-memory-30b-a3b.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
- Hy-Memory-30B-A3B, good for Agents with an external memory framework that want a local model for the write path on a 24 GB card Ahead on Reach, 85 against 55; Risk, 60 against 45; Documentation and upkeep, 68 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 Agent interface, 75 against 65.

| Category | Hy-Memory-30B-A3B | Baidu Unlimited-OCR-2 |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 85 | 55 |
| Risk (20%) | 60 | 45 |
| Agent interface (10%) | 65 | 75 |
| Documentation and upkeep (10%) | 68 | 50 |

| Fact (where they differ) | Hy-Memory-30B-A3B | Baidu Unlimited-OCR-2 |
| --- | --- | --- |
| Vendor | Tencent (Hy team) | 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 | 2026-10-16 | 2026-10-26 |

Why the edge:
- Reach, Hy-Memory-30B-A3B +30: Hy-Memory-30B-A3B 85 (Memory 25, Tencent's own Q4_K_M GGUF is 18.24 GB, and 18.24 GB × 1.2 = 21.9 GB, which fits 24 GB but not 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.)
- Documentation and upkeep, Hy-Memory-30B-A3B +18: Hy-Memory-30B-A3B 68 (Model card 8, Intended use (the write path of Mem0, MemOS and Hy-Memory), parameters (30B, about 3B active) and languages (English and Chinese, in the metadata)…); 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, Hy-Memory-30B-A3B +15: Hy-Memory-30B-A3B 60 (File safety 25, 51 safetensors shards and no pickle or Python files.); 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 +10: Hy-Memory-30B-A3B 65 (Chat template 20, chat_template.jinja in the repository.); 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.)