Ollama v0.40.0-rc3 釋出:允許 RC 版本拉取匹配的最小版本
v0.40.0-rc3: pull: allow RCs to pull matching min_version (#18790)
重點導讀
Ollama 在 v0.40.0-rc3 版本中,預設在 Apple Silicon 上使用 MLX 執行模型,並新增 gemma4、qwen3.6、qwen3.5 等模型,決策模型也可在 MLX 上執行。
AI 伴隨問答
針對這篇報導有疑問?可直接點選快捷問題或向 AI 追問背景脈絡與技術細節:
正文
What's Changed
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.
ollama pull qwen3.8
ollama run qwen3.8
Additional models include gemma4, qwen3.6 and qwen3.5
Decision models are now available on MLX as well: Nimble tev1 clef clef-flash
We will continue testing and enabling additional models.
Full Changelog: v0.34.4...v0.40.0-rc3
來源: ollama release (github.com)
開啟原文