Edge0 open-sources on-device framework running 35B models in 1-2.5GB of memory
FinanceYF5 · x · 2026-09-10
Edge0 is now open source, releasing its 8B and 35B models along with runtime and inference code. The headline result: a 35B language model runs fully on-device on an iPhone using only 1-2.5GB of peak memory — no cloud, no remote server, no desktop GPU.
The framework also enables fully on-device generation for games, 3D scenes, and web content. The team invites edge-AI developers to try it and give feedback.
Related event: Edge0 Open-Sources On-Device MoE Framework with 35B Model(2 posts)→
More from Infra
- Anthropic S-1: training infra edge cut per-task cost 40% and doubled revenue growth — BenBajarin · 2026-10-26
- Rewriting scaling law study: optimal synthetic data share rises from 10% to 32% with compute — heghbalz · 2026-10-26
- US states halt new data centers as 72% of Americans oppose local builds — YvesMulkers · 2026-10-26
- $5M Seed Round Can't Afford One DeepSeek Training Run: GPU-less AI Startup's Three Paths — FinanceYF5 · 2026-10-26
- HBM demand shifts: low-stack inference plans shelved, Rubin to go 12-high only — BenBajarin · 2026-10-26
- CircuitHub unveils The Grid, a factory-scale robot making PCBs in the US twice as fast as Shenzhen — garrytan · 2026-10-26