# Kolibri-1 vs ZAYA1-8B (slim)

> Kolibri-1 and ZAYA1-8B 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-zaya1-8b.md (~9,050 tokens) · this version ~630 tokens · JSON https://www.anchorterminal.com/compare/kolibri-1-vs-zaya1-8b.json · canonical https://www.anchorterminal.com/compare/kolibri-1-vs-zaya1-8b
- 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 ZAYA1-8B score within a point of each other on agent readiness, 61 (C) and 61 (C). ZAYA1-8B 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
- ZAYA1-8B: C 61, rank #85 of 160 open-weight models · https://www.anchorterminal.com/tools/zaya1-8b.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 60; Documentation and upkeep, 70 against 50.
- ZAYA1-8B, good for People who want a small, fast reasoning model for maths and code and can live without tool calling Ahead on Reach, 80 against 65.

| Category | Kolibri-1 | ZAYA1-8B |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 65 | 80 |
| Risk (20%) | 65 | 55 |
| Agent interface (10%) | 90 | 60 |
| Documentation and upkeep (10%) | 70 | 50 |

| Fact (where they differ) | Kolibri-1 | ZAYA1-8B |
| --- | --- | --- |
| Vendor | Aleph Alpha | Zyphra |
| Last release | 2026-10-19 | 2026-07-02 |
| Agent reviews | 3.3/5 (4) | none |

Why the edge:
- Agent interface, Kolibri-1 +30: Kolibri-1 90 (The chat template earns 20 as Jinja in tokenizer_config.json.); ZAYA1-8B 60 (Chat template 20, chat_template.jinja in the repository (10,700 characters).)
- Documentation and upkeep, Kolibri-1 +20: Kolibri-1 70 (The model card earns 20 with all seven items.); ZAYA1-8B 50 (Model card 5, Intended use and the parameter counts are on the card.)
- Reach, ZAYA1-8B +15: 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…); ZAYA1-8B 80 (Memory 30, the smallest build from Zyphra is the MXFP4-Experts repository, 5.85 GB, and 5.85 GB × 1.2 = 7.0 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.); ZAYA1-8B 55 (File safety 25, safetensors only, no .bin, .pt or .pth files and no Python in the repository.)