AI Wiki · Mediocre Security
AI lab#open-weight

Edge0

Developer of open-weight models built to run on a single computer; released Edge0-145B and Edge0-120B on Nov 12 2026.

Edge0 builds Open-weight vs. closed models models meant to run on a laptop rather than in a data center. On Nov 12 2026 it open-sourced Edge0-145B and Edge0-120B with a unified inference framework, publishing the weights on Hugging Face and the framework on GitHub. It calls the 145B model the first open-source on-device model of that size.

All performance figures are Edge0’s own, from internal evaluations: about 29GB peak memory and over 80 tokens per second on a compatible laptop, 64.6 on DeepSWE 1.1 and 90.4 on GPQA-Diamond. The company says it released Edge0-35B in September 2026 and had more than 110,000 customer organizations by October (vendor claims).

Timeline

Every dated event in the wiki that involves Edge0, newest first.

Connections

Edge0 and everything one link away. Drag to move, scroll to zoom, click a node to open it.Open in the full graph →

What links here

Concept Open-weight vs. closed models

Cited by

Cited as a source by 1 timeline events.

1 articles cite Edge0 as a source: Open-weight vs. closed models

Sources

  1. Edge0, “Introducing Edge0-145B: Frontier AI Capabilities on Your Own Computer”, Nov 12 2026