Liquid AI d1-2B decision model runs on-device: ~68ms gesture reading, 14 decisions/s, zero tokens
AccBalanced · x · 2026-11-16
A demo runs Liquid AI's d1-2B decision model via mlx-vlm on an Apple Silicon M5 Max MacBook: it reads gestures and expressions from a webcam in 68ms, makes 14 decisions per second, generates zero tokens, and runs 100% locally.
More from Infra
- Microsoft Outlook outage silenced chlorine alert emails at German theme park, injuring 15 pool guests — AccBalanced · 2026-11-16
- Ming-Chi Kuo: OpenAI and Anthropic orders extend Google TPU visibility to 2029, ~26M units — BenBajarin · 2026-11-16
- Cerebras core revenue up 70% YoY to $231M, backlog hits $26.1B — AccBalanced · 2026-11-16
- Nvidia CEO saga: firstadopter discusses Jensen Huang's resignation and successor race on TBPN — firstadopter · 2026-11-16
- Bittensor week: Lium hits $35M annualized GPU rental run rate — bittingthembits · 2026-11-16
- AI summary of data center permitting reveals a dizzying list of required reforms — PTrubey · 2026-11-16