ds4
Run large language models like Qwen on consumer hardware using SSD-streamed mixture-of-experts.
Why it made the shelf
The GitHub repository provides a developer tool for running large AI models locally with constrained hardware by.
- First seen
- 2 months ago
- Best score
- 24 points · 4 comments
Behind the tool
Who built it. How it grew.
People, backing, growth, and ownership. Every claim links to its source.
Official sitegithub.com
Source review current
Public trail
Where it showed up
1 reference from 1 publisher.
- First trace
- Hacker News2 months ago
- Discussion
- 4 comments
- 01Hacker NewsFirst trace
Qwen3.6-35B-A3B on a 16 GB M1 Pro with SSD-streamed MoE
