SemiAnalysis: Rubin NVL72 delivers 7x perf-per-watt over GB300, far above Jensen's 3x claim
inductionheads · x · 2026-09-17
SemiAnalysis reports that at GTC 2026 Jensen Huang claimed only 3x better perf-per-watt for Rubin NVL72 versus GB300 NVL72 — but its own testing shows 7x better perf-per-watt, arguing NVIDIA is "underpromising and overdelivering." If confirmed, this materially improves the cost economics of large-scale training and inference.
Related event: SemiAnalysis Finds Rubin NVL72 Far Exceeds Nvidia's Claimed Gains(3 posts)→
More from Infra
- VC-Attention: training-free low-bit attention hits 1.9x on B200, beating FlashAttention-4 — xiuyu_l · 2026-09-17
- mlx.fast fixes speed-display bug: MLX kernels hit 80.6 tps, nearing 100% speedup milestone — HankYeomans · 2026-09-17
- Memory shortage hits checkout: Xiaomi raises phone prices 200-1,000 yuan as DRAM stock dips under 10 days — tengyanAI · 2026-09-17
- Burkov Slams OpenRouter Reliability: Fallback Models Fail Together — burkov · 2026-09-17
- Common Crawl puts crawl archives on Hugging Face Storage Bucket, with a getting-started guide — vanstriendaniel · 2026-09-17
- Anthropic Signs A$32B Queensland Data Center Deal, Claude's First Australian Footprint — ocean_protocol · 2026-09-17