2026-04-07T20:27:55.742Z · Src: 2026-04-07T00:00:00.000Z
2026-04-04T16:23:25.819Z · Src: 2026-04-04T00:00:00.000Z
2026-04-03T03:04:59.000Z · ★ 80
# AMD Lemonade：支持 GPU 和 NPU 的开源本地 AI 服务器 AMD 发布了 **Lemonade**——一个快速、开源的本地 AI 服务器，可在 GPU 和 NPU 上运行，使开发者和用户能够在自己的硬件上私密运行多个 AI 模型。 ## 什么是 Lemonade？ Lemonade 是一个轻量级、本地优先的 AI 服务器，为多种 AI 模态提供统一 API： - *
2026-04-03T03:04:56.000Z · ★ 80
# AMD Lemonade: Open Source Local AI Server for Text, Images, and Speech AMD has released **Lemonade**, a fast, open source local AI server that runs on both GPUs and NPUs, enabling developers and us
2026-04-02T12:16:22.000Z · ★ 80
# AMD Lemonade：支持 GPU 和 NPU 的开源本地 AI 服务器 AMD 发布了 **Lemonade**，一款快速、开源的本地 AI 服务器，可在 GPU 和 NPU 上运行文本、图像和语音模型。该工具代表了 AMD 向本地 AI 推理市场推进的举措，挑战 NVIDIA CUDA 生态系统的主导地位。 ## 什么是 Lemonade？ Lemonade 是一个轻量级 AI
2026-04-02T12:16:19.000Z · ★ 80
# AMD Lemonade: Open Source Local AI Server Supporting GPU and NPU AMD has released **Lemonade**, a fast, open-source local AI server that runs text, image, and speech models on both GPUs and NPUs. T
2026-03-31T12:14:20.027Z · Src: 2026-03-31T12:00:00.000Z
2026-03-31T11:28:44.415Z · Src: 2026-03-31T12:00:00.000Z
2026-03-20T20:34:30.000Z
A new HomeSec-Bench benchmark shows Qwen3.5-9B running locally on a MacBook Pro M5 achieves 93.8% accuracy on security tasks, just 4 points behind GPT-5.4 cloud — with zero API costs and full privacy.
2026-03-18T13:12:43.000Z
OnPrem.LLM's AgentExecutor enables launching autonomous AI agents with 9 built-in tools (file ops, shell, web search) that work with both cloud and local models, featuring sandboxed execution and work