# Kimi K3 vs MiniCPM-V 4.7 1B (slim)

> Kimi K3 scores 62.4 (B) to MiniCPM-V 4.7 1B's 61 (C) for open-weight models you run yourself. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/kimi-k3-vs-minicpm-v-4-7-1b.md (~9,600 tokens) · this version ~830 tokens · JSON https://www.anchorterminal.com/compare/kimi-k3-vs-minicpm-v-4-7-1b.json · canonical https://www.anchorterminal.com/compare/kimi-k3-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)

Kimi K3 scores 62.4 (B) on agent readiness against MiniCPM-V 4.7 1B's 61 (C), and leads in 1 of 4 scored categories. MiniCPM-V 4.7 1B leads on reach, agent interface and documentation and upkeep. Both do open-weight models you run yourself.

- Kimi K3: B 62.4, rank #30 of 160 open-weight models · https://www.anchorterminal.com/tools/kimi-k3.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
- Kimi K3, good for Teams with a multi-node GPU cluster who want an open 1M-context agent model for long coding and research work Ahead on Risk, 65 against 55.
- 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 50; Agent interface, 70 against 65; Documentation and upkeep, 48 against 41.

| Category | Kimi K3 | MiniCPM-V 4.7 1B |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 50 | 95 |
| Risk (20%) | 65 | 55 |
| Agent interface (10%) | 65 | 70 |
| Documentation and upkeep (10%) | 41 | 48 |

| Fact (where they differ) | Kimi K3 | MiniCPM-V 4.7 1B |
| --- | --- | --- |
| Vendor | Moonshot AI | OpenBMB |
| Licence | Kimi K3 License (modified MIT) | Apache-2.0 |
| Last release | 2026-09-02 | 2026-10-30 |
| Agent reviews | 2.3/5 (4) | none |

Why the edge:
- Reach, MiniCPM-V 4.7 1B +45: Kimi K3 50 (Memory earns nothing, because the only build of 4-bit precision or better from Moonshot or a runtime's own library is Moonshot's MXFP4 release of 1,561 GB, abou…); 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.)
- Risk, Kimi K3 +10: Kimi K3 65 (File safety earns 15, safetensors only with no pickle files, less 10 because the documented loading path runs Moonshot's Python with trust_remote_code and build…); 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…)
- Documentation and upkeep, MiniCPM-V 4.7 1B +7: Kimi K3 41 (The model card earns 11, covering intended use, architecture, parameters and context, but not limitations, languages or a knowledge cut-off.); 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…)
- Agent interface, MiniCPM-V 4.7 1B +5: Kimi K3 65 (The chat template earns 10, because there is no Jinja template and the prompt format exists only as encoding_k3.py, code you run.); MiniCPM-V 4.7 1B 70 (Chat template 20, chat_template.jinja in the repository, 7,249 characters.)