Qualcomm Hexagon NPU
PulseAugur coverage of Qualcomm Hexagon NPU — every cluster mentioning Qualcomm Hexagon NPU across labs, papers, and developer communities, ranked by signal.
- 2026-06-11 research_milestone A new paper details an energy-efficient RAG pipeline running on a mobile NPU, achieving significant speed and energy improvements over CPU and GPU baselines. source
2 day(s) with sentiment data
-
Hugging Face releases LFM3 multimodal models for specialized edge AI
Hugging Face has released LFM3, a new family of Liquid Foundation Models designed for specialized intelligence. These models feature a tri-hybrid architecture and a new training recipe, enabling LFM3-1.7B to outperform …
-
On-device LLM engines NobodyWho and RunAnywhere compared for speed and features
A comparison of two on-device LLM inference engines, NobodyWho and RunAnywhere, reveals significant differences in performance and licensing. While both are built on llama.cpp and support various mobile development fram…
-
Mobile NPU enables energy-efficient on-device RAG
Researchers have developed an energy-efficient Retrieval-Augmented Generation (RAG) pipeline that runs entirely on a mobile Neural Processing Unit (NPU), specifically the Qualcomm Hexagon NPU found in the Snapdragon X E…