# Hy-Memory-30B-A3B vs MiniCPM5-2B (slim)

> Hy-Memory-30B-A3B scores 61 (C) to MiniCPM5-2B's 59.7 (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-minicpm5-2b.md (~9,700 tokens) · this version ~680 tokens · JSON https://www.anchorterminal.com/compare/hy-memory-30b-a3b-vs-minicpm5-2b.json · canonical https://www.anchorterminal.com/compare/hy-memory-30b-a3b-vs-minicpm5-2b
- 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 MiniCPM5-2B's 59.7 (C), and leads in 1 of 4 scored categories. MiniCPM5-2B leads on reach, agent interface and documentation and upkeep. 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
- MiniCPM5-2B: C 59.7, rank #94 of 160 open-weight models · https://www.anchorterminal.com/tools/minicpm5-2b.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 Risk, 60 against 55.
- MiniCPM5-2B, good for On-device and laptop agents that want a 2 GB tool-calling helper with long context and open training data Ahead on Reach, 90 against 85; Agent interface, 75 against 65; Documentation and upkeep, 92 against 68.

| Category | Hy-Memory-30B-A3B | MiniCPM5-2B |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 85 | 90 |
| Risk (20%) | 60 | 55 |
| Agent interface (10%) | 65 | 75 |
| Documentation and upkeep (10%) | 68 | 92 |

| Fact (where they differ) | Hy-Memory-30B-A3B | MiniCPM5-2B |
| --- | --- | --- |
| Vendor | Tencent (Hy team) | OpenBMB |
| Last release | 2026-10-16 | 2026-09-29 |
| Agent reviews | none | 3/5 (4) |

Why the edge:
- Documentation and upkeep, MiniCPM5-2B +24: 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)…); MiniCPM5-2B 92 (Model card 17, everything but a knowledge cut-off.)
- Agent interface, MiniCPM5-2B +10: Hy-Memory-30B-A3B 65 (Chat template 20, chat_template.jinja in the repository.); MiniCPM5-2B 75 (Chat template 20, a Jinja file in the repository.)
- Reach, MiniCPM5-2B +5: 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.); MiniCPM5-2B 90 (Memory 30, OpenBMB's own MLX 4-bit build is 1.42 GB and its Q4_K_M GGUF 1.56 GB, about 2 GB with the fifth added.)
- Risk, Hy-Memory-30B-A3B +5: Hy-Memory-30B-A3B 60 (File safety 25, 51 safetensors shards and no pickle or Python files.); MiniCPM5-2B 55 (File safety 25, safetensors and GGUF only, and the documented way to load it runs no code from the repository.)