AION
Open-source releaseMLOps, Tooling & Infrastructure1 source · Sep 25, 2026

ollama/ollama v0.40.0

Models run on MLX on Apple Silicon by default

AppleOllamaMLX
← Back to brief

Key points

  • In this release, on Apple Silicon devices, model architectures supported by the MLX runtime will automatically run on MLX.
  • We will continue testing and enabling additional models.

Sources (1)

  • [1]ollama/ollama v0.40.0
    GitHub: ollama/ollama · Sep 25, 03:31 AM
    **Models run on MLX on Apple Silicon by default**
    In this release, on Apple Silicon devices, model architectures supported by the MLX runtime will automatically run on MLX.

Extractive summary: sentences quoted from the sources.