NVIDIA Claims HGX Rubin NVL8 Delivers 10x More Tokens per Megawatt Than B200
thursdai_pod · x · 2026-10-27
NVIDIA reports HGX Rubin NVL8 delivers 10x more tokens per megawatt than HGX B200, with @WolframRvnwlf sighting one at GTC Berlin. Thursdai pod's new "From the Forge" episode, powered by CoreWeave, covers Rubin hardware, Reflection's Beam on serverless inference, and RL rollouts.
Related event: NVIDIA Claims Rubin NVL8 Delivers 10x B200 Tokens-per-Megawatt(2 posts)→
More from Infra
- AI Infra Meme: While Countries Need TW-Scale Power for Datacenters, People Argue About Lightbulbs — mgostIH · 2026-10-27
- Legora runs 2,000 parallel agent evals on Modal Sandboxes for legal AI — blelbach · 2026-10-27
- Cloud release velocity scores: AWS 95, Azure 90, Google Cloud 82 — DavidLinthicum · 2026-10-27
- Selling a 5090 to scale local inference: one business weighs 5 hardware paths — Anarchaotic · 2026-10-27
- AWS tutorial: fleet-wide edge CV model lifecycle with SageMaker SDK v3, ~$0.07 per run — AWS ML Blog · 2026-10-27
- Qwen3.8-27B hits 40 tok/s on Jetson Thor with INT4 + MTP, accuracy beats FP16 — No-Dragonfly6246 · 2026-10-27