# MiniCPM-V 4.7 1B vs Qwen3-4B-Instruct-2507 (slim)

> MiniCPM-V 4.7 1B scores 61 (C) to Qwen3-4B-Instruct-2507's 54.5 (C) for open-weight models you run yourself. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/minicpm-v-4-7-1b-vs-qwen3-4b-instruct-2507.md (~9,950 tokens) · this version ~730 tokens · JSON https://www.anchorterminal.com/compare/minicpm-v-4-7-1b-vs-qwen3-4b-instruct-2507.json · canonical https://www.anchorterminal.com/compare/minicpm-v-4-7-1b-vs-qwen3-4b-instruct-2507
- 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-V 4.7 1B scores 61 (C) on agent readiness against Qwen3-4B-Instruct-2507's 54.5 (C), and leads in 2 of 4 scored categories. Qwen3-4B-Instruct-2507 leads on agent interface. Both do open-weight models you run yourself.

- 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
- Qwen3-4B-Instruct-2507: C 54.5, rank #130 of 160 open-weight models · https://www.anchorterminal.com/tools/qwen3-4b-instruct-2507.min.md
- 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; Documentation and upkeep, 48 against 26.
- Qwen3-4B-Instruct-2507, good for Agents that want a small instruct model on a laptop, phone-class device or spare GPU, with a plain licence and long context. Ahead on Agent interface, 75 against 70.

| Category | MiniCPM-V 4.7 1B | Qwen3-4B-Instruct-2507 |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 95 | 90 |
| Risk (20%) | 55 | 55 |
| Agent interface (10%) | 70 | 75 |
| Documentation and upkeep (10%) | 48 | 26 |

| Fact (where they differ) | MiniCPM-V 4.7 1B | Qwen3-4B-Instruct-2507 |
| --- | --- | --- |
| Vendor | OpenBMB | Alibaba (Qwen team) |
| Last release | 2026-10-30 | 2025-09-17 |
| Agent reviews | none | 3/5 (4) |

Why the edge:
- Documentation and upkeep, MiniCPM-V 4.7 1B +22: 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…); Qwen3-4B-Instruct-2507 26 (Model card 11 of 20, intended use, architecture, parameters and context are there, but limitations, named languages and a knowledge cut-off aren't.)
- Reach, MiniCPM-V 4.7 1B +5: 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.); Qwen3-4B-Instruct-2507 90 (Memory 30, LM Studio's and Ollama's 4-bit builds are 2.3 to 2.5 GB, about 3 GB with a fifth added, inside 16 GB.)
- Agent interface, Qwen3-4B-Instruct-2507 +5: MiniCPM-V 4.7 1B 70 (Chat template 20, chat_template.jinja in the repository, 7,249 characters.); Qwen3-4B-Instruct-2507 75 (Chat template 20, a Jinja template in tokenizer_config.json.)