Intel hosts 816B-param Muse Spark Open air-cooled on four 160GB D-series GPUs
BenBajarin · x · 2026-10-16
Intel announced Day 0 support for Meta's Muse Spark Open, hosting the 816B-parameter model on just four 160GB air-cooled Intel GPU D-series cards plus Xeon CPUs—an enterprise play built on flexible, memory-intensive deployment. Intel calls it the most capable U.S. open-weights model to date. Analyst Ben Bajarin says there's more strategy in the move than is obvious, sharing OCP floor photos of the dual-die D270 card and copper cold plate.
More from Infra
- FT warns of 'Darwin moment' for AI borrowers as CoreWeave bonds sink to distress levels — firstadopter · 2026-10-16
- Phone as interface, home servers as the lab: a two-workflow local AI setup — EAccelerate_42 · 2026-10-16
- "A datacenter is a bank": CoreWeave drama revives calls for算力 supervision — arthurcolle · 2026-10-16
- DOT-MoE: converting dense models into sparse MoE via optimal transport — burkov · 2026-10-16
- Stanford CS336: A 7B model needs 14GB for weights but 84GB to train — stanfordnlp · 2026-10-16
- New NVFP4 trick: compressing block scales saves 45-48% per expert matrix, bit-exact — TheZachMueller · 2026-10-16