Running K3 on 4 H100s with RoCE
TheZachMueller · x · 2026-07-17
The author plans to use a somewhat "jank" supercomputer/cloud infrastructure setup to run K3 once it is released.
The specific configuration involves 4 H100 nodes interconnected via RoCE. The post focuses on the compute and networking stack required for local/private deployment rather than the model itself.
More from Infra
- Actual Computer says its inference stack is tuned for Nvidia’s consumer Blackwell lineup — markjeffrey · 2026-07-22
- Ben Bajarin says CPU demand is still being badly underestimated — BenBajarin · 2026-07-22
- An energy model says the U.S. could run short of natural gas starting in 2028 — churchkey · 2026-07-22
- Devin adds e2b sandboxes for remote agent execution — badphilosopher · 2026-07-22
- Arbitrum fee simulation shows higher gas capacity but lower L2 revenue under ArbOS61 — tomwanhh · 2026-07-22
- NVIDIA pushes OpenUSD as the common layer for simulation and physical AI — MonaJalal_ · 2026-07-22