# Kolibri-1 vs Qwen-AgentWorld-35B-A3B (slim)

> Kolibri-1 scores 61 (C) to Qwen-AgentWorld-35B-A3B's 52.1 (D) for open-weight models you run yourself. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/kolibri-1-vs-qwen-agentworld-35b-a3b.md (~10,000 tokens) · this version ~730 tokens · JSON https://www.anchorterminal.com/compare/kolibri-1-vs-qwen-agentworld-35b-a3b.json · canonical https://www.anchorterminal.com/compare/kolibri-1-vs-qwen-agentworld-35b-a3b
- 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 Qwen-AgentWorld-35B-A3B's 52.1 (D), and leads in every scored category. 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
- Qwen-AgentWorld-35B-A3B: D 52.1, rank #141 of 160 open-weight models · https://www.anchorterminal.com/tools/qwen-agentworld-35b-a3b.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 Reach, 65 against 55; Risk, 65 against 55; Agent interface, 90 against 50; Documentation and upkeep, 70 against 41.
- Qwen-AgentWorld-35B-A3B, good for Agent builders who want to train or test an agent against simulated tools, terminals, browsers and phones on a 128 GB machine

| Category | Kolibri-1 | Qwen-AgentWorld-35B-A3B |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 65 | 55 |
| Risk (20%) | 65 | 55 |
| Agent interface (10%) | 90 | 50 |
| Documentation and upkeep (10%) | 70 | 41 |

| Fact (where they differ) | Kolibri-1 | Qwen-AgentWorld-35B-A3B |
| --- | --- | --- |
| Vendor | Aleph Alpha | Alibaba (Qwen team) |
| Last release | 2026-10-19 | 2026-06-25 |
| Agent reviews | 3.3/5 (4) | none |

Why the edge:
- Agent interface, Kolibri-1 +40: Kolibri-1 90 (The chat template earns 20 as Jinja in tokenizer_config.json.); Qwen-AgentWorld-35B-A3B 50 (Chat template 20, chat_template.jinja in the repository, the same as the template in tokenizer_config.json.)
- Documentation and upkeep, Kolibri-1 +29: Kolibri-1 70 (The model card earns 20 with all seven items.); Qwen-AgentWorld-35B-A3B 41 (Model card 11, the card gives intended use (simulating agent environments), architecture, parameters and context length.)
- Reach, Kolibri-1 +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…); Qwen-AgentWorld-35B-A3B 55 (Memory 10, Alibaba's only build is the BF16 safetensors, 69.32 GB, and 69.32 GB × 1.2 = 83.2 GB, above 64 GB and inside the reference machine's GPU share.)
- Risk, Kolibri-1 +10: Kolibri-1 65 (File safety earns 25 for safetensors only, with no repository code run on load.); Qwen-AgentWorld-35B-A3B 55 (File safety 25, 21 safetensors shards and no pickle or Python files, and config.json has no auto_map.)