# Foundry Local vs MLX LM (slim)

> Foundry Local scores 60.5 (C) on agent readiness against MLX LM's 52.2 (D), and leads in 6 of 7 scored categories. Both do local inference. Category scores, facts, verdicts and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/foundry-local-vs-mlx-lm.md (~2,550 tokens) · this version ~580 tokens · JSON https://www.anchorterminal.com/compare/foundry-local-vs-mlx-lm.json · canonical https://www.anchorterminal.com/compare/foundry-local-vs-mlx-lm
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-09

Foundry Local scores 60.5 (C) on agent readiness against MLX LM's 52.2 (D), and leads in 6 of 7 scored categories. Both do local inference.

- Foundry Local: C 60.5, rank #461 of 842 · https://www.anchorterminal.com/tools/foundry-local.min.md
- MLX LM: D 52.2, rank #657 of 842 · https://www.anchorterminal.com/tools/mlx-lm.min.md
- Foundry Local, good for An application that ships a model to end users' Windows, macOS or Linux devices and wants NPU and GPU variants chosen automatically, especially on Windows. Ahead on Schema & documentation, 53 against 37; Agent ergonomics, 61 against 54; Security & auth, 39 against 32; Maintenance & community, 88 against 61; Transparency & trust, 72 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.

| Category | Foundry Local | MLX LM |
| --- | --- | --- |
| Reliability (16%) | 68 | 66 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 53 | 37 |
| Agent ergonomics (13%) | 61 | 54 |
| Security & auth (14%) | 39 | 32 |
| Payments & pricing (10%) | 60 | 60 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 88 | 61 |
| Transparency & trust (7%) | 72 | 66 |

| Fact (where they differ) | Foundry Local | MLX LM |
| --- | --- | --- |
| Kind | SDK + MCP | HTTP API |
| Vendor | Microsoft | Apple Inc. |
| Licence | MIT for the SDKs and the v2 native runtime. The CLI is closed source under Microsoft Software Licence Terms. Execution providers carry NVIDIA, Intel and Qualcomm licences, and each model carries its own | MIT |
| Last release | 2026-09-29 | 2026-10-01 |
| Popularity | 2.6k stars, 105k npm/wk, 47k PyPI/wk | 7.3k stars, 140k PyPI/wk |