# MiniCPM-V 4.7 35B-A3B vs Nanbeige4.3-33B (slim)

> MiniCPM-V 4.7 35B-A3B and Nanbeige4.3-33B score within a point of each other for open-weight models you run yourself, 61 and 60.8 out of 100. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/minicpm-v-4-7-35b-a3b-vs-nanbeige-4-3-33b.md (~9,900 tokens) · this version ~780 tokens · JSON https://www.anchorterminal.com/compare/minicpm-v-4-7-35b-a3b-vs-nanbeige-4-3-33b.json · canonical https://www.anchorterminal.com/compare/minicpm-v-4-7-35b-a3b-vs-nanbeige-4-3-33b
- 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 35B-A3B and Nanbeige4.3-33B score within a point of each other on agent readiness, 61 (C) and 60.8 (C). Nanbeige4.3-33B leads on risk and agent interface. Both do open-weight models you run yourself.

- MiniCPM-V 4.7 35B-A3B: C 61, rank #77 of 160 open-weight models · https://www.anchorterminal.com/tools/minicpm-v-4-7-35b-a3b.min.md
- Nanbeige4.3-33B: C 60.8, rank #86 of 160 open-weight models · https://www.anchorterminal.com/tools/nanbeige-4-3-33b.min.md
- MiniCPM-V 4.7 35B-A3B, good for Agents that need to read screenshots, documents and video on a local machine with 24 to 32 GB for the model, under a permissive licence Ahead on Reach, 90 against 80; Documentation and upkeep, 68 against 56.
- Nanbeige4.3-33B, good for Agents with a 32 GB GPU (INT4) or more, or the 128 GB reference machine at BF16, that want an Apache-tagged 33B model for long coding and tool loops. Ahead on Risk, 60 against 55; Agent interface, 85 against 70.

| Category | MiniCPM-V 4.7 35B-A3B | Nanbeige4.3-33B |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 90 | 80 |
| Risk (20%) | 55 | 60 |
| Agent interface (10%) | 70 | 85 |
| Documentation and upkeep (10%) | 68 | 56 |

| Fact (where they differ) | MiniCPM-V 4.7 35B-A3B | Nanbeige4.3-33B |
| --- | --- | --- |
| Vendor | OpenBMB | Nanbeige LLM Lab (BOSS Zhipin) |
| Licence | Apache-2.0 | Apache-2.0 (Hub metadata only; the repository has no LICENSE file) |
| Last release | 2026-11-03 | 2026-10-31 |

Why the edge:
- Agent interface, Nanbeige4.3-33B +15: MiniCPM-V 4.7 35B-A3B 70 (Chat template 20, a Jinja file in the repository.); Nanbeige4.3-33B 85 (The chat template earns 20, Jinja in tokenizer_config.json.)
- Documentation and upkeep, MiniCPM-V 4.7 35B-A3B +12: MiniCPM-V 4.7 35B-A3B 68 (Model card 8, it covers intended use, architecture and parameters but not limitations, context length, languages or a knowledge cut-off.); Nanbeige4.3-33B 56 (The model card earns 11, with intended use, parameters, context and languages but no limitations, architecture or cut-off.)
- Reach, MiniCPM-V 4.7 35B-A3B +10: MiniCPM-V 4.7 35B-A3B 90 (Memory 25, since OpenBMB's IQ4_XS GGUF with its vision projector is 19.6 GB and needs about 23.6 GB with the fifth added, which fits 24 GB, while its Q4_K_M GGU…); Nanbeige4.3-33B 80 (Memory earns 20, since Nanbeige's INT4 build is 22.57 GB, about 27 GB with a fifth added, which fits 32 GB.)
- Risk, Nanbeige4.3-33B +5: MiniCPM-V 4.7 35B-A3B 55 (File safety 25, safetensors and GGUF only, no Python in the main repository and no remote code needed.); Nanbeige4.3-33B 60 (File safety earns 25, safetensors only and no repository code, so the card's trust_remote_code has nothing to run.)