# Open-weight models you download and run yourself (slim)

> 3 open-weight models ranked by the Anchor benchmark. Leader Kolibri-1 (BB). Model weights you download and run on your own hardware, under a licence that says what you may do with them. Each is graded on the files, apart from any hosted API that serves the same model. Compared on the licence, the runtimes that load it, tool calling, context, the memory it needs and what the vendor publishes about training data and evaluations.

- Full: https://www.anchorterminal.com/categories/open-weights.md (~1,450 tokens) · this version ~280 tokens · JSON https://www.anchorterminal.com/categories/open-weights.json · canonical https://www.anchorterminal.com/categories/open-weights
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-10-20
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

- Tools: 3 · agent-ready (BB+): 1 · accept x402: 0 · JSON: https://www.anchorterminal.com/api/v1/tools.json · by capability: https://www.anchorterminal.com/api/v1/capabilities.json
- Capabilities: model.open-weights

| # | Tool | Grade | Score | Confidence | x402 | Auth | Where | Slim |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 47 | Kolibri-1 | BB | 75.8 | medium | no | None | local | https://www.anchorterminal.com/tools/kolibri-1.min.md |
| 428 | Qwen3.8-27B | B | 63.7 | medium | no | None | local | https://www.anchorterminal.com/tools/qwen3-8-27b.min.md |
| 472 | DeepSeek V4.1 Flash | B | 62.8 | medium | no | None | local | https://www.anchorterminal.com/tools/deepseek-v4-1-flash.min.md |