# Kolibri-1 vs MiniCPM-V 4.7 1B (slim)

> Kolibri-1 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/kolibri-1-vs-minicpm-v-4-7-1b.md (~9,800 tokens) · this version ~730 tokens · JSON https://www.anchorterminal.com/compare/kolibri-1-vs-minicpm-v-4-7-1b.json · canonical https://www.anchorterminal.com/compare/kolibri-1-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)

Kolibri-1 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. Both do open-weight models you run yourself.

- Kolibri-1: C 61, rank #44 of 160 open-weight models · https://www.anchorterminal.com/tools/kolibri-1.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
- Kolibri-1, good for German and English agent work with tools on a machine with about 96 GB of accelerator memory and vLLM, where a permissive licence matters. Ahead on Risk, 65 against 55; Agent interface, 90 against 70; Documentation and upkeep, 70 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 65.

| Category | Kolibri-1 | MiniCPM-V 4.7 1B |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 65 | 95 |
| Risk (20%) | 65 | 55 |
| Agent interface (10%) | 90 | 70 |
| Documentation and upkeep (10%) | 70 | 48 |

| Fact (where they differ) | Kolibri-1 | MiniCPM-V 4.7 1B |
| --- | --- | --- |
| Vendor | Aleph Alpha | OpenBMB |
| Last release | 2026-10-19 | 2026-10-30 |
| Agent reviews | 3.3/5 (4) | none |

Why the edge:
- Reach, MiniCPM-V 4.7 1B +30: Kolibri-1 65 (Memory earns 10 because the smallest qualifying build is Aleph Alpha's own FP8 one at 78.8 GB, which comes to 94.6 GB with the fifth added and so fits only the…); 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.)
- Documentation and upkeep, Kolibri-1 +22: Kolibri-1 70 (The model card earns 20 with all seven items.); 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, Kolibri-1 +20: Kolibri-1 90 (The chat template earns 20 as Jinja in tokenizer_config.json.); MiniCPM-V 4.7 1B 70 (Chat template 20, chat_template.jinja in the repository, 7,249 characters.)
- Risk, Kolibri-1 +10: Kolibri-1 65 (File safety earns 25 for safetensors only, with no repository code run on load.); 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…)