# Kolibri-1 vs Nanbeige4.2-3B (slim)

> Kolibri-1 and Nanbeige4.2-3B 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-nanbeige-4-2-3b.md (~9,300 tokens) · this version ~680 tokens · JSON https://www.anchorterminal.com/compare/kolibri-1-vs-nanbeige-4-2-3b.json · canonical https://www.anchorterminal.com/compare/kolibri-1-vs-nanbeige-4-2-3b
- 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 Nanbeige4.2-3B score within a point of each other on agent readiness, 61 (C) and 61 (C). Nanbeige4.2-3B 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
- Nanbeige4.2-3B: C 61, rank #78 of 160 open-weight models · https://www.anchorterminal.com/tools/nanbeige-4-2-3b.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 85.
- Nanbeige4.2-3B, good for Local agents that need tool calling and a long context on a laptop or a small GPU Ahead on Reach, 85 against 65.

| Category | Kolibri-1 | Nanbeige4.2-3B |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 65 | 85 |
| Risk (20%) | 65 | 55 |
| Agent interface (10%) | 90 | 85 |
| Documentation and upkeep (10%) | 70 | 72 |

| Fact (where they differ) | Kolibri-1 | Nanbeige4.2-3B |
| --- | --- | --- |
| Vendor | Aleph Alpha | Nanbeige LLM Lab (BOSS Zhipin) |
| Licence | Apache-2.0 | Apache-2.0 (Hub metadata only; the repository has no LICENSE file) |
| Last release | 2026-10-19 | 2026-09-11 |
| Agent reviews | 3.3/5 (4) | none |

Why the edge:
- Reach, Nanbeige4.2-3B +20: 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…); Nanbeige4.2-3B 85 (Memory 30, the smallest build from Nanbeige is the FP8 repository (the 8-bit GPTQ one is the same size), 5.19 GB, and 5.19 GB × 1.2 = 6.2 GB, within 16 GB.)
- Risk, Kolibri-1 +10: Kolibri-1 65 (File safety earns 25 for safetensors only, with no repository code run on load.); Nanbeige4.2-3B 55 (File safety 15, safetensors only, no .bin, .pt or .pth files (25).)
- Agent interface, Kolibri-1 +5: Kolibri-1 90 (The chat template earns 20 as Jinja in tokenizer_config.json.); Nanbeige4.2-3B 85 (Chat template 20, A Jinja chat template in tokenizer_config.json (7,961 characters), with enable_thinking, preserve_thinking, tools and tool_call_format switche…)