RTX Spark desktops swap 200G ConnectX-7 for 10GbE, killing two-box clusters for large MoEs
AIFlow_ML · x · 2026-11-21
New RTX Spark desktops share the Grace CPU and Blackwell GPU class with DGX Spark but ship 10GbE instead of ConnectX-7. Without the 200G link, two-box clustering for large MoE inference is off the table. The author, who runs local inference on DGX Spark, advises buying the box with the 200G port if you might cluster later.
More from Infra
- Optical waveguide crossing lets light pass through while keeping circuits electrically isolated — jwt0625 · 2026-11-21
- Inkling 2 Mini quantized to 13.9GB runs at ~60 t/s decode on a single RTX 4090 — indrasmirror · 2026-11-21
- Sentdex: RTX PRO 6K stock returning and prices falling as loopholes close — good for consumers — Sentdex · 2026-11-21
- Son approached Wall Street to fund a $1T SK Hynix buyout, per Bloomberg scoop — tengyanAI · 2026-11-21
- Early Inkling 2 Mini LoRA tests: same results with under a third of the energy — ziqiao_ma · 2026-11-21
- AMD AI DevDay Paris on Dec 12: vLLM Maintainer to Talk Decode Optimization, Free ROCm Cert — AccBalanced · 2026-11-21