Ollama v0.40.0-rc6 版新增多模態嵌入功能
v0.40.0-rc6: model: add multimodal embeddings (#18820)
重點導讀
Ollama v0.40.0-rc6 版在 Apple Silicon 上自動使用 MLX 執行模型,並首次支援多模態嵌入。
- MLX 執行:Apple Silicon 裝置上,支援的模型架構將自動跑在 MLX。
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 · 原文
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