# Cola2 vs Kolibri-1 (slim)

> Kolibri-1 scores 61 (C) to Cola2's 33.9 (F) for open-weight models you run yourself. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/cola2-vs-kolibri-1.md (~8,750 tokens) · this version ~680 tokens · JSON https://www.anchorterminal.com/compare/cola2-vs-kolibri-1.json · canonical https://www.anchorterminal.com/compare/cola2-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 Cola2's 33.9 (F), and leads in every scored category. Both do open-weight models you run yourself.

- Cola2: F 33.9, rank #160 of 160 open-weight models · https://www.anchorterminal.com/tools/cola2.min.md
- Kolibri-1: C 61, rank #44 of 160 open-weight models · https://www.anchorterminal.com/tools/kolibri-1.min.md
- Cola2, good for Researchers working on latent or diffusion language models who want a checkpoint to study
- 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 25; Risk, 65 against 40; Agent interface, 90 against 20; Documentation and upkeep, 70 against 58.

| Category | Cola2 | Kolibri-1 |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 25 | 65 |
| Risk (20%) | 40 | 65 |
| Agent interface (10%) | 20 | 90 |
| Documentation and upkeep (10%) | 58 | 70 |

| Fact (where they differ) | Cola2 | Kolibri-1 |
| --- | --- | --- |
| Vendor | ByteDance (Seed) | Aleph Alpha |
| Licence | None stated for the weights (the code is Apache 2.0) | Apache-2.0 |
| Last release | 2026-11-06 | 2026-10-19 |
| Agent reviews | none | 3.3/5 (4) |

Why the edge:
- Agent interface, Kolibri-1 +70: Cola2 20 (Chat template 20, A chat template in tokenizer_config.json (4,116 characters), which came with the Qwen3 tokenizer.); Kolibri-1 90 (The chat template earns 20 as Jinja in tokenizer_config.json.)
- Reach, Kolibri-1 +40: Cola2 25 (Memory 15, the only build is the F32 safetensors set, 35.07 GB, and 35.07 GB × 1.2 = 42.1 GB, within 64 GB.); 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 +25: Cola2 40 (File safety 15, safetensors only, no .bin, .pt or .pth files (25).); Kolibri-1 65 (File safety earns 25 for safetensors only, with no repository code run on load.)
- Documentation and upkeep, Kolibri-1 +12: Cola2 58 (Model card 8, Intended use and limitations (the out-of-scope list, and the unconverged latent model) and the architecture are on the card and the GitHub model c…); Kolibri-1 70 (The model card earns 20 with all seven items.)