# Arete-27B vs Kolibri-1 (slim)

> Kolibri-1 scores 61 (C) to Arete-27B's 55.1 (C) for open-weight models you run yourself. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/arete-27b-vs-kolibri-1.md (~8,800 tokens) · this version ~630 tokens · JSON https://www.anchorterminal.com/compare/arete-27b-vs-kolibri-1.json · canonical https://www.anchorterminal.com/compare/arete-27b-vs-kolibri-1
- 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 scores 61 (C) on agent readiness against Arete-27B's 55.1 (C), and leads in every scored category. Both do open-weight models you run yourself.

- Arete-27B: C 55.1, rank #123 of 160 open-weight models · https://www.anchorterminal.com/tools/arete-27b.min.md
- Kolibri-1: C 61, rank #44 of 160 open-weight models · https://www.anchorterminal.com/tools/kolibri-1.min.md
- Arete-27B, good for Agents that want Qwen3.8-27B's coding and tool use without its handling of politically sensitive topics, on a 24 GB card or a 128 GB machine
- 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 Reach, 65 against 50; Risk, 65 against 55; Agent interface, 90 against 60; Documentation and upkeep, 70 against 63.

| Category | Arete-27B | Kolibri-1 |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 50 | 65 |
| Risk (20%) | 55 | 65 |
| Agent interface (10%) | 60 | 90 |
| Documentation and upkeep (10%) | 63 | 70 |

| Fact (where they differ) | Arete-27B | Kolibri-1 |
| --- | --- | --- |
| Vendor | Nous Research | Aleph Alpha |
| Last release | 2026-11-06 | 2026-10-19 |
| Agent reviews | none | 3.3/5 (4) |

Why the edge:
- Agent interface, Kolibri-1 +30: Arete-27B 60 (Chat template 20, a Jinja file in the repository.); Kolibri-1 90 (The chat template earns 20 as Jinja in tokenizer_config.json.)
- Reach, Kolibri-1 +15: Arete-27B 50 (Memory 10, the only build from Nous Research is the 54.7 GB BF16 release, which needs about 66 GB and fits the reference machine.); 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…)
- Risk, Kolibri-1 +10: Arete-27B 55 (File safety 25, safetensors only and no remote code.); Kolibri-1 65 (File safety earns 25 for safetensors only, with no repository code run on load.)
- Documentation and upkeep, Kolibri-1 +7: Arete-27B 63 (Model card 8, no limitations, context length, languages or cut-off.); Kolibri-1 70 (The model card earns 20 with all seven items.)