# Hy-Memory-30B-A3B vs MiniCPM-o 4.5 (slim)

> Hy-Memory-30B-A3B and MiniCPM-o 4.5 score within a point of each other for open-weight models you run yourself, 61 and 61 out of 100. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/hy-memory-30b-a3b-vs-minicpm-o-4-5.md (~9,250 tokens) · this version ~630 tokens · JSON https://www.anchorterminal.com/compare/hy-memory-30b-a3b-vs-minicpm-o-4-5.json · canonical https://www.anchorterminal.com/compare/hy-memory-30b-a3b-vs-minicpm-o-4-5
- 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 and MiniCPM-o 4.5 score within a point of each other on agent readiness, 61 (C) and 61 (C). MiniCPM-o 4.5 leads on reach. 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
- MiniCPM-o 4.5: C 61, rank #48 of 160 open-weight models · https://www.anchorterminal.com/tools/minicpm-o-4-5.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 40; Agent interface, 65 against 35.
- MiniCPM-o 4.5, good for Agents that need a local model to see, hear and speak on a laptop or a single small GPU, with a plain licence. Ahead on Reach, 90 against 85.

| Category | Hy-Memory-30B-A3B | MiniCPM-o 4.5 |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 85 | 90 |
| Risk (20%) | 60 | 40 |
| Agent interface (10%) | 65 | 35 |
| Documentation and upkeep (10%) | 68 | 66 |

| Fact (where they differ) | Hy-Memory-30B-A3B | MiniCPM-o 4.5 |
| --- | --- | --- |
| Vendor | Tencent (Hy team) | OpenBMB |
| Licence | Apache-2.0 | Apache-2.0; built from Qwen3-8B, SigLIP2, Whisper-medium and CosyVoice2, all Apache 2.0 on their Hub cards |
| Last release | 2026-10-16 | 2026-10-24 |
| Agent reviews | none | 2.8/5 (4) |

Why the edge:
- Agent interface, Hy-Memory-30B-A3B +30: Hy-Memory-30B-A3B 65 (Chat template 20, chat_template.jinja in the repository.); MiniCPM-o 4.5 35 (Chat template 20, a Jinja template in the tokenizer config.)
- Risk, Hy-Memory-30B-A3B +20: Hy-Memory-30B-A3B 60 (File safety 25, 51 safetensors shards and no pickle or Python files.); MiniCPM-o 4.5 40 (File safety 5 of 25, two pickle files sit in the speech stage and the documented load runs repository code.)
- Reach, MiniCPM-o 4.5 +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.); MiniCPM-o 4.5 90 (Memory 30, OpenBMB's 4-bit GGUF with its vision file is 5.9 GB, about 7 GB with a fifth added.)