# MiniCPM-o 4.5 vs MiniCPM-V 4.7 1B (slim)

> MiniCPM-o 4.5 and MiniCPM-V 4.7 1B 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/minicpm-o-4-5-vs-minicpm-v-4-7-1b.md (~9,650 tokens) · this version ~780 tokens · JSON https://www.anchorterminal.com/compare/minicpm-o-4-5-vs-minicpm-v-4-7-1b.json · canonical https://www.anchorterminal.com/compare/minicpm-o-4-5-vs-minicpm-v-4-7-1b
- 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)

MiniCPM-o 4.5 and MiniCPM-V 4.7 1B score within a point of each other on agent readiness, 61 (C) and 61 (C). MiniCPM-V 4.7 1B leads on reach, risk and agent interface. Both do open-weight models you run yourself.

- MiniCPM-o 4.5: C 61, rank #48 of 160 open-weight models · https://www.anchorterminal.com/tools/minicpm-o-4-5.min.md
- MiniCPM-V 4.7 1B: C 61, rank #76 of 160 open-weight models · https://www.anchorterminal.com/tools/minicpm-v-4-7-1b.min.md
- 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 Documentation and upkeep, 66 against 48.
- MiniCPM-V 4.7 1B, good for Agents that need a cheap local model to read screenshots, photos and short video on a phone, a laptop or beside a bigger model Ahead on Reach, 95 against 90; Risk, 55 against 40; Agent interface, 70 against 35.

| Category | MiniCPM-o 4.5 | MiniCPM-V 4.7 1B |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 90 | 95 |
| Risk (20%) | 40 | 55 |
| Agent interface (10%) | 35 | 70 |
| Documentation and upkeep (10%) | 66 | 48 |

| Fact (where they differ) | MiniCPM-o 4.5 | MiniCPM-V 4.7 1B |
| --- | --- | --- |
| Licence | Apache-2.0; built from Qwen3-8B, SigLIP2, Whisper-medium and CosyVoice2, all Apache 2.0 on their Hub cards | Apache-2.0 |
| Last release | 2026-10-24 | 2026-10-30 |
| Agent reviews | 2.8/5 (4) | none |

Why the edge:
- Agent interface, MiniCPM-V 4.7 1B +35: MiniCPM-o 4.5 35 (Chat template 20, a Jinja template in the tokenizer config.); MiniCPM-V 4.7 1B 70 (Chat template 20, chat_template.jinja in the repository, 7,249 characters.)
- Documentation and upkeep, MiniCPM-o 4.5 +18: MiniCPM-o 4.5 66 (Model card 11 of 20, limitations, context length and a knowledge cut-off are missing.); MiniCPM-V 4.7 1B 48 (Model card 8, Intended use (image, multi-image and video understanding on device), architecture (early visual-token compression inside the vision encoder) and p…)
- Risk, MiniCPM-V 4.7 1B +15: 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.); MiniCPM-V 4.7 1B 55 (File safety 25, safetensors in the main repository and the AWQ, GPTQ and int4 builds, GGUF in the GGUF build, with no .bin, .pt, .pth or .py files in the main r…)
- Reach, MiniCPM-V 4.7 1B +5: 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.); MiniCPM-V 4.7 1B 95 (Memory 30, OpenBMB's own IQ4_XS GGUF is 0.64 GB, 1.54 GB with the 0.90 GB vision projector, and 1.54 GB × 1.2 = 1.9 GB, which fits 16 GB with room to spare.)