PulseAugur
中
实时 19:13:23
English(EN) Ollama v0.40.2 Models downloaded with earlier versions of Ollama are upgraded in the background the first time you run them, for better performance and compatib

Ollama发布v0.40.2版本,支持自动模型升级和Apple Silicon上的MLX

Ollama发布了多个更新,包括v0.40.2、v0.40.1和v0.40.0版本。最新发布的v0.40.2版本引入了对先前下载模型的自动后台升级,以提高性能并与llama.cpp兼容。v0.40.1版本包括对服务器API代理的更改,修复了Windows与llama.cpp的兼容性问题,并移除了CLI入门流程中的账户设置步骤。v0.40.0版本引入的一项重要功能是在Apple Silicon设备上默认使用MLX运行模型。 AI

影响 提高了在各种硬件上本地运行AI模型的用户的性能和兼容性。

排序理由 这是一个工具软件发布,不是前沿模型发布或重要的行业事件。

在 Mastodon — mastodon.social 阅读 →

AI 生成摘要 · Google Gemini · 来自 4 个来源。 我们如何撰写摘要 →

Ollama发布v0.40.2版本,支持自动模型升级和Apple Silicon上的MLX

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
这是一个工具软件发布,不是前沿模型发布或重要的行业事件。
Source corroboration
4 independent sources
Strong cross-source corroboration — multiple independent publishers covered this within the clustering window.
Topics
product, infra
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
46 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [4]

  1. Mastodon — fosstodon.org TIER_1 English(EN) · [email protected] ·

    ⚙️ Ollama 新版本发布!⚙️ 版本:v0.40.2 发行说明:## 模型升级 使用早期 Ollama 版本下载的模型将在后台升级

    ⚙️ New Ollama Release! ⚙️ Version: v0.40.2 Release Notes: ## Model upgrades Models downloaded with earlier versions of Ollama are upgraded in the background the first time you run them, for better performance and compatibility when running on llama.cpp. To make downgrading safe, …

  2. Mastodon — fosstodon.org TIER_1 English(EN) · [email protected] ·

    ⚙️ Ollama 新版本发布!⚙️ 版本:v0.40.1 发布说明:## 变更内容 * server: 代理云使用和余额 API by @drifkin in https:// github.com/olla

    ⚙️ New Ollama Release! ⚙️ Version: v0.40.1 Release Notes: ## What's Changed * server: proxy cloud usage and balance APIs by @drifkin in https:// github.com/ollama/ollama/pull/ 18829 * llama: fix clef head reads past 2GiB on windows by @Gigrise in https:// github.com/ollama/ollama…

  3. Mastodon — fosstodon.org TIER_1 English(EN) · [email protected] ·

    ⚙️ Ollama 新版本发布!⚙️ 版本:v0.40.0 发布说明:## 变更内容 **默认在 Apple Silicon 上使用 MLX 运行模型** 在此版本中,在 Apple Silicon 上

    ⚙️ New Ollama Release! ⚙️ Version: v0.40.0 Release Notes: ## 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 …

  4. Mastodon — mastodon.social TIER_1 English(EN) · whatsnew_fyi ·

    使用早期版本 Ollama 下载的模型,在您首次运行时会在后台升级,以获得更好的性能和兼容性

    Ollama v0.40.2 Models downloaded with earlier versions of Ollama are upgraded in the background the first time you run them, for better performance and compatibility when running on llama.cpp. https:// whatsnew.fyi/product/ollama/re leases/v0.40.2-rc0 # Ollama # AI