# Kolibri-1 vs Ornith-1.5-122B (slim)

> Kolibri-1 and Ornith-1.5-122B 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-ornith-1-5-122b.md (~9,550 tokens) · this version ~730 tokens · JSON https://www.anchorterminal.com/compare/kolibri-1-vs-ornith-1-5-122b.json · canonical https://www.anchorterminal.com/compare/kolibri-1-vs-ornith-1-5-122b
- 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 Ornith-1.5-122B score within a point of each other on agent readiness, 61 (C) and 61 (C). Ornith-1.5-122B 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
- Ornith-1.5-122B: C 61, rank #81 of 160 open-weight models · https://www.anchorterminal.com/tools/ornith-1-5-122b.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 50; Agent interface, 90 against 85; Documentation and upkeep, 70 against 36.
- Ornith-1.5-122B, good for Local coding and terminal agents on a 128 GB unified-memory machine or a 96 GB GPU setup, where a clear licence file and an answering publisher aren't required Ahead on Reach, 75 against 65.

| Category | Kolibri-1 | Ornith-1.5-122B |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 65 | 75 |
| Risk (20%) | 65 | 50 |
| Agent interface (10%) | 90 | 85 |
| Documentation and upkeep (10%) | 70 | 36 |

| Fact (where they differ) | Kolibri-1 | Ornith-1.5-122B |
| --- | --- | --- |
| Vendor | Aleph Alpha | Ornith |
| Licence | Apache-2.0 | MIT |
| Last release | 2026-10-19 | 2026-10-24 |
| Agent reviews | 3.3/5 (4) | none |

Why the edge:
- Documentation and upkeep, Kolibri-1 +34: Kolibri-1 70 (The model card earns 20 with all seven items.); Ornith-1.5-122B 36 (Model card 11, it covers intended use, architecture, parameters and context but not limitations, languages or a knowledge cut-off.)
- Risk, Kolibri-1 +15: Kolibri-1 65 (File safety earns 25 for safetensors only, with no repository code run on load.); Ornith-1.5-122B 50 (File safety 25, safetensors and GGUF only and no Python in any of Ornith's repositories for this size, so the card's --trust-remote-code flag loads nothing from…)
- Reach, Ornith-1.5-122B +10: 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…); Ornith-1.5-122B 75 (Memory 10, since Ornith's own MLX 4-bit build is 69.7 GB and needs about 83.6 GB with the fifth added, over 64 GB and inside the reference machine's 107.4 GB, a…)
- Agent interface, Kolibri-1 +5: Kolibri-1 90 (The chat template earns 20 as Jinja in tokenizer_config.json.); Ornith-1.5-122B 85 (Chat template 20, a Jinja file in the repository.)