# Docker Model Runner vs MLX LM (slim)

> Docker Model Runner scores 57.1 (C) on agent readiness against MLX LM's 52.2 (D), and leads in 5 of 7 scored categories. MLX LM leads on maintenance & community. Both do local inference. Category scores, facts, verdicts and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/docker-model-runner-vs-mlx-lm.md (~2,700 tokens) · this version ~680 tokens · JSON https://www.anchorterminal.com/compare/docker-model-runner-vs-mlx-lm.json · canonical https://www.anchorterminal.com/compare/docker-model-runner-vs-mlx-lm
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-09

Docker Model Runner scores 57.1 (C) on agent readiness against MLX LM's 52.2 (D), and leads in 5 of 7 scored categories. MLX LM leads on maintenance & community. Both do local inference.

- Docker Model Runner: C 57.1, rank #559 of 842 · https://www.anchorterminal.com/tools/docker-model-runner.min.md
- MLX LM: D 52.2, rank #657 of 842 · https://www.anchorterminal.com/tools/mlx-lm.min.md
- 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 66; Schema & documentation, 49 against 37; Security & auth, 40 against 32; Transparency & trust, 73 against 66.
- MLX LM, good for An owner with an Apple silicon Mac who wants MLX-format models, local fine-tuning and quantisation from Python or the command line, with a simple local chat completions server. Ahead on Maintenance & community, 61 against 55. Also No incidents deducted, where Docker Model Runner loses 3 points for them.

| Category | Docker Model Runner | MLX LM |
| --- | --- | --- |
| Reliability (16%) | 85 | 66 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 49 | 37 |
| Agent ergonomics (13%) | 58 | 54 |
| Security & auth (14%) | 40 | 32 |
| Payments & pricing (10%) | 60 | 60 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 55 | 61 |
| Transparency & trust (7%) | 73 | 66 |

| Fact (where they differ) | Docker Model Runner | MLX LM |
| --- | --- | --- |
| Vendor | Docker, Inc. | Apple Inc. |
| Licence | 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 | MIT |
| llms.txt | yes | no |
| Last release | 2026-08-12 | 2026-10-01 |
| Terms last updated | 2026-08-26 | no document linked |
| Privacy policy last updated | 2026-08-26 | no document linked |
| 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 | 656 stars | 7.3k stars, 140k PyPI/wk |