Edge0 Framework Runs Qwen 35B AI Model from Your SSD
TL;DR
Edge0, an open source framework introduced by The Stack, lets a 35-billion-parameter Qwen Mixture of Experts (MoE) model run directly from storage instead of loading all weights into active memory. According to the report, this cuts the memory footprint to about 2.9 GB and streams further model parts from the SSD on demand, so large models could run on devices with limited RAM.
Nauti's Take
For small teams, the first test should be a real local workflow with Edge0 and Qwen 35B on existing hardware, measuring latency, power use, and SSD activity. The low RAM footprint could be useful, yet it says little about day-to-day usability if storage access makes responses sluggish, and the current report offers no solid benchmark data.
Video
Sources
