Qualcomm says Snapdragon's Hexagon NPU now runs 30B+ parameter MoE models on-device
samcharrington · x · 2026-09-23
At Snapdragon Summit, Qualcomm's Chris Patrick highlighted the growing mobile inference capabilities of Snapdragon processors and the Hexagon NPU, which now support running 30B+ parameter MoE models on-device — pushing the ceiling for on-device LLMs even higher.
More from Infra
- KubeCon keynote: computing is shifting from human speed to agent speed — HowDevelop · 2026-11-12
- Leaked memo: Meta infrastructure head Santosh Janardhan to leave in early 2027 — dinabass · 2026-11-12
- Omarchy 4.6 lets you share local AI models across your tailnet, says DHH — alexcovo_eth · 2026-11-12
- Eric Schmidt's foundation funds French NGO fighting against data centers — StephanSturges · 2026-11-12
- Epoch: Open-Weight GLM 5.3 Hacks Six Firefox Versions for ~$1,000 Each; Claude Fable 5.2 Sets ECI Record — Epoch AI · 2026-11-12
- Polymarket prices 28% odds of a state data center moratorium; Torus raises $500M — Polymarket · 2026-11-12