NVIDIA Unveils Rubin Architecture: 288GB HBM4 and 22TB/s Bandwidth
charles_irl · x · 2026-07-22
NVIDIA executive Kyle Kranen pulled back the curtains on the upcoming Rubin architecture, designed specifically to maximize agentic tokens per watt.
Key hardware specs include:
- Compute: 50 Petaflops of sparse NVFP4 compute
- Memory: 288 GB HBM4 with 22TB/s of bandwidth
- Interconnect: NVLink 6 delivering 3.6TB/s of bandwidth
The architecture will also introduce a suite of new performance features.
Related event: NVIDIA Launches Vera Rubin with 10x Energy Efficiency(6 posts)→
More from Infra
- Engram's random reads don't suit SSDs; CPU-memory over NVLink could serve all 72 GPUs — bookwormengr · 2026-09-11
- 80% of the DIY LLM inference hype posters have already quit — it's brutally hard systems work — abhijithneil · 2026-09-11
- Hugging Face's Ultra Scale Playbook: a free book on training LLMs on GPU clusters — mdancho84 · 2026-09-11
- Is inference latency becoming the biggest bottleneck for production AI agents? — Euphoric_Sea632 · 2026-09-11
- LLM Serving Metrics Thread: Why TPOT and Uptime Make or Break User Experience — abhijithneil · 2026-09-11
- PlanetScale launches sharded Postgres: 768 servers acting as one, 1PB scale — dhruv2038 · 2026-09-11