# Berth vs Docker Model Runner (slim)

> Berth scores 67.6 (B) to Docker Model Runner's 57.2 (C) for local inference. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/berth-vs-docker-model-runner.md (~3,000 tokens) · this version ~730 tokens · JSON https://www.anchorterminal.com/compare/berth-vs-docker-model-runner.json · canonical https://www.anchorterminal.com/compare/berth-vs-docker-model-runner
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-10-28
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

Berth scores 67.6 (B) on agent readiness against Docker Model Runner's 57.2 (C), and leads in 4 of 7 scored categories. Docker Model Runner leads on reliability and transparency & trust. Both do local inference.

- Berth: B 67.6, rank #283 of 1218 · https://www.anchorterminal.com/tools/berth.min.md
- Docker Model Runner: C 57.2, rank #714 of 1218 · https://www.anchorterminal.com/tools/docker-model-runner.min.md
- Berth, good for Someone running several GPU programs (llama.cpp, llama-swap, Ollama, vLLM, ComfyUI, games) on one NVIDIA card who wants them to take turns, and agents that need to ask for the card. Ahead on Schema & documentation, 69 against 49; Agent ergonomics, 75 against 58; Security & auth, 51 against 40; Maintenance & community, 76 against 55. Also No incidents deducted, where Docker Model Runner loses 3 points for them.
- Docker Model Runner, good for A team that already runs Docker and wants local models served to containers and Compose services through OpenAI-, Anthropic- or Ollama-compatible routes, with models stored as OCI artefacts. Ahead on Reliability, 85 against 76; Transparency & trust, 74 against 68. Also No key needed to call it.

| Category | Berth | Docker Model Runner |
| --- | --- | --- |
| Reliability (16%) | 76 | 85 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 69 | 49 |
| Agent ergonomics (13%) | 75 | 58 |
| Security & auth (14%) | 51 | 40 |
| Payments & pricing (10%) | 60 | 60 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 76 | 55 |
| Transparency & trust (7%) | 68 | 74 |

| Fact (where they differ) | Berth | Docker Model Runner |
| --- | --- | --- |
| Vendor | Trevin Tindall (T-Crypt on GitHub) | Docker, Inc. |
| Auth | API key | None |
| Licence | Apache-2.0. The Berth name, the Pilot mascot and the artwork in assets/ are excluded from the licence, per the NOTICE file | Apache-2.0 (server, CLI plugin and `dmr` binary). Docker Desktop, which bundles it, is closed software under Docker's subscription agreement, and each model carries its own licence |
| llms.txt | no | yes |
| Last release | 2026-10-23 | 2026-08-12 |
| Terms last updated | no document linked | 2026-08-26 |
| Privacy policy last updated | no document linked | 2026-08-26 |
| Customer content may train models |  | not found in the text |
| Terms restrict automated access |  | yes |
| Terms restrict benchmarking |  | yes |
| Terms or service can change without notice |  | not found in the text |
| Arbitration or class-action waiver |  | yes |
| Popularity | 245 stars | 656 stars |