Exo Buys Two More DGX Sparks to Push Local Inference Amid Open-Weights Ban Fears
kuchaev · x · 2026-11-16
The Exo team (open-source distributed inference) showed off two newly purchased NVIDIA DGX Spark units (plus Samsung 9100 PRO 2TB SSDs), vowing to keep improving local inference amid talk of banning open weights. The photo also shows two Acer Veriton AI Mini Workstations, another NVIDIA-accelerated small AI box.
More from Infra
- China, not the US, is blocking H200 sales; analyst calls chip policy decade's biggest self-own — firstadopter · 2026-11-16
- Agents need throwaway DB copies, not mocks — copy-on-write cloning may become default infra — petrusenko_max · 2026-11-16
- Self-hosted daily game pipeline runs Qwen3.6-35B and Qwen-Image locally on DGX Spark, zero API fees — jbsan · 2026-11-16
- audio.cpp ships real-time local avatar voice chat: ~850ms latency on RTX 5090 — Acceptable-Cycle4645 · 2026-11-16
- Local real-time talking-head voice chat lands in audio.cpp 0.9.4 with ~850ms latency on RTX 5090 — Acceptable-Cycle4645 · 2026-11-16
- Bessent questions on TV whether Nvidia pressed "seemingly illicit sales" to boost revenue — ShakeelHashim · 2026-11-16