Qualcomm's next-gen Hexagon NPU runs 30B MoE models with 32K context on-device
lee_stott · x · 2026-09-11
Qualcomm detailed its next-gen Hexagon NPU for Snapdragon devices: a new Element Accelerator for transformers, +50% shared memory, 32K context window, the ability to run 30B-parameter MoE models (3B active per token), and +50% INT4 prefill speed — a big step for agentic on-device AI.
Related event: Qualcomm's Next-Gen Hexagon NPU to Run 30B MoE Models On-Device(3 posts)→
More from Embodied
- π0.5 study: raising demos from 10 to 438 lifts Place Ball in Bowl success from 7% to 83% — stingning · 2026-10-27
- GPT-6 Astra controls dexterous hands zero-shot at just 5.2% success in 500 trials — stingning · 2026-10-27
- HandsOn benchmark: 66 verified tasks and 18,000 human demos for dexterous manipulation — stingning · 2026-10-27
- DexPort: a handheld interface with a real robot hand for dexterous-hand data collection — pabbeel · 2026-10-27
- ROS names Alejandro Hernández Cordero new project lead, eyes 2027 release — ___Mufasaa · 2026-10-27
- ROS Meetup coming to Google's NYC office Oct 29 with speakers from Tangent, Cohesive Robotics, Intrinsic — kscottz · 2026-10-27