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.

Original post →

More from Infra

Infra channel →