Reka EdgeQ VLM Runs Natively on Snapdragon 8 Elite NPU With 0.73s First Token
RekaAILabs · x · 2026-09-23
Reka launched Reka EdgeQ, an on-device VLM running natively on Qualcomm Snapdragon 8 Elite's Hexagon NPU for wearables and phones: 0.73s time-to-first-token on images, +34 pts over Gemma 4 E4B on MLVU video benchmarks, and 6.9 mWh per inference (3x lower heat overhead). They custom-tuned a ConvNeXt V2 vision encoder/decoder for the NPU, keeping the GPU idle to avoid thermal throttling.
More from Infra
- Gas-for-AI-datacenters forum co-located with CoRL shows energy demand spillover — carlosdponx · 2026-11-12
- a16z podcast: Mike Volpi on Cisco's 70+ acquisition playbook and the AI buildout — a16z · 2026-11-12
- AMD to pass Intel in server revenue by mid-2027 as share gains 6 points a year — BenBajarin · 2026-11-12
- Study: Reflective Data Center Roofs Actually Cool Daytime Ground by 1.8-2.2°C — SumitGup · 2026-11-12
- Tsinghua's BaGuaLu-2 tames MoE expert-load spikes at runtime, accepted to SC26 — jiqizhixin · 2026-11-12
- antirez backs low-bit DeepSeek 4.1 Flash over Qwen 27B dense on Apple M5 Macs — antirez · 2026-11-12