NVIDIA at IFA 2026: 1.9x faster local inference, PAIR router, RTX Spark PCs in October
nordicinst · x · 2026-09-04
At IFA 2026, NVIDIA announced up to 1.9x faster local inference via new llama.cpp and vLLM optimizations (also in LM Studio and Ollama), NVIDIA PAIR — a Personal AI Router that spreads inference across PCs on a home network — and compact RTX Spark Windows PCs from Lenovo and Acer arriving in October. New local-capable models include 30B Nemotron 3.5 Lightning, Z.ai's GLM-5.3-Flash MoE, and Qwen3.8-Flash-Next / Qwen3.8-27B open-weight models for DGX Spark and DGX Station.
More from Embodied
- ePlane unveils full-scale 2.2-tonne eVTOL prototype e200X-PT01 built in Chennai — vaibhavbetter · 2026-10-21
- "Robots are going underground, figuring out their own routes" — a look past chatbot debates — VraserX · 2026-10-21
- Deepak Pathak: There Is No Perfect Data Source for Robotics — chris_j_paxton · 2026-10-21
- Discrete action representations match or beat continuous ones for robot policies — GuanyaShi · 2026-10-21
- Developer gave his Grok bot $1,000 to build itself a body — parts keep arriving — Baconbrix · 2026-10-21
- Tuesday Labs opens $200 reservations for 999 numbered Voxel Series-1 home robots — testingcatalog · 2026-10-21