Skip to content
Hacker News front page

Frontier 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.

Why it matters: Tim Dettmers' dlab open source week released local inference and agent systems that run 125B and 550B models on a single 24 GB GPU and a 128 GB memory device.

Read the original ↗Export Markdown