# MiniCPM5-2B vs WeVisOne-VL-2B (slim)

> WeVisOne-VL-2B 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/minicpm5-2b-vs-wevisone-vl-2b.md (~9,050 tokens) · this version ~630 tokens · JSON https://www.anchorterminal.com/compare/minicpm5-2b-vs-wevisone-vl-2b.json · canonical https://www.anchorterminal.com/compare/minicpm5-2b-vs-wevisone-vl-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)

WeVisOne-VL-2B scores 61 (C) on agent readiness against MiniCPM5-2B's 59.7 (C), and leads in 0 of 4 scored categories. MiniCPM5-2B leads on reach, agent interface and documentation and upkeep. Both do open-weight models you run yourself.

- MiniCPM5-2B: C 59.7, rank #94 of 160 open-weight models · https://www.anchorterminal.com/tools/minicpm5-2b.min.md
- WeVisOne-VL-2B: C 61, rank #83 of 160 open-weight models · https://www.anchorterminal.com/tools/wevisone-vl-2b.min.md
- 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 70; Agent interface, 75 against 70; Documentation and upkeep, 92 against 48.
- WeVisOne-VL-2B, good for Agents that need to locate, count or cut out objects in images on a small GPU, under a permissive licence

| Category | MiniCPM5-2B | WeVisOne-VL-2B |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 90 | 70 |
| Risk (20%) | 55 | 55 |
| Agent interface (10%) | 75 | 70 |
| Documentation and upkeep (10%) | 92 | 48 |

| Fact (where they differ) | MiniCPM5-2B | WeVisOne-VL-2B |
| --- | --- | --- |
| Vendor | OpenBMB | Tencent (WeChat Vision) |
| Last release | 2026-09-29 | 2026-10-28 |
| Terms last updated | no document linked | not read yet |
| Agent reviews | 3/5 (4) | none |

Why the edge:
- Documentation and upkeep, MiniCPM5-2B +44: MiniCPM5-2B 92 (Model card 17, everything but a knowledge cut-off.); WeVisOne-VL-2B 48 (Model card 8, Intended use, limitations and the architecture are on the card.)
- Reach, MiniCPM5-2B +20: 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.); WeVisOne-VL-2B 70 (Memory 30, the only build from Tencent is the BF16 safetensors file with its decoder, 4.92 GB, and 4.92 GB × 1.2 = 5.9 GB, within 16 GB.)
- Agent interface, MiniCPM5-2B +5: MiniCPM5-2B 75 (Chat template 20, a Jinja file in the repository.); WeVisOne-VL-2B 70 (Chat template 20, chat_template.jinja in the repository (5,292 characters), Qwen3-VL's template.)