Release

Ollama 0.40.0 runs supported models on MLX by default on Apple Silicon

Event: Oct 6, 2026 · Published: Oct 13, 2026

Ollama published version 0.40.0 on GitHub on October 6, 2026, after a series of release candidates that began with v0.40.0-rc0 on September 25. According to the release notes, model architectures supported by the MLX runtime now run on MLX automatically on Apple Silicon devices, with models listed including qwen3.8, gemma4, qwen3.6, and qwen3.5. The notes say decision models (Nimble, tev1, clef, and clef-flash) and the embeddinggemma-2 embedding model are also available on MLX, and that Ollama will continue testing and enabling additional models. USASI has not tested this release.1 2

Ollama

Sources

1.
Ollama v0.40.0 (GitHub release notes) (external site: github.com)
Ollama · Release notes · published Oct 6, 2026 · accessed Oct 13, 2026
2.
Ollama v0.40.0-rc0 (GitHub pre-release) (external site: github.com)
Ollama · Release notes · published Sep 25, 2026 · accessed Oct 13, 2026

Email a correction Report a correction Edit this entry

All news

Cite this page

APA style

USASI. (2026, October 13). Ollama 0.40.0 runs supported models on MLX by default on Apple Silicon. United States of America Superintelligence. https://unitedstatesofamericasuperintelligence.com/news/ollama-0-40-0-runs-models-on-mlx-by-default/

BibTeX

@misc{usasi_news_ollama_0_40_0_runs_models_on_mlx_by_default,
  author = {{USASI}},
  title = {Ollama 0.40.0 runs supported models on MLX by default on Apple Silicon},
  year = {2026},
  month = oct,
  howpublished = {\url{https://unitedstatesofamericasuperintelligence.com/news/ollama-0-40-0-runs-models-on-mlx-by-default/}},
  note = {United States of America Superintelligence. Last updated 2026-10-13}
}

The date is when this page was last updated. Add the date you read it if your style needs one.

Related catalog entries

Sources

Share or cite this page

Support Us