Trending storyPast story
Frontier AI on Your Own Hardware
1 report1 sourceupdated 8 days ago
What happened
Summary
Tim Dettmers 的 dlab 这周会开源一整套工具，目标是让前沿 AI 能在本地硬件上跑起来。他们放出了一个能自己优化 Metal 内核的智能体，把 Qwen 3.6 35B-A3B 模型压到每个权重只占 1.5 比特，在 Mac 上跑出了每秒 450 个 token 的速度。核心观点是，现在做研究的基本单位不再是单篇论文，而是一套能互相配合...
Coverage
Follow the reports to see the story from different sides.
Sep 22
- Hacker News front pagePickFrontier AI on Your Own Hardware
Tim Dettmers's dlab is open-sourcing a full stack this week to run frontier AI on local hardware. An agent auto-optimized Metal kernels to run Qwen 3.6 35B-A3B at 1.5 bits per weight, hitting 450 tokens/s on a Mac. The core argument: the unit of research is no longer the paper but a coherent ecosystem. Full details are still under wraps, but the release includes an autonomous research agent, efficient test-time scaling, and auto-compaction that beats Claude Code on token savings.