NVIDIA Vera Rubin NVL72 delivers 30x higher efficiency for AI agents vs GB300
nvidia · x · 2026-08-24
NVIDIA released the first on-silicon performance data for Vera Rubin, measured on real-world agentic workloads using the DeepSeek V4 Pro model and SemiAnalysis AgentX benchmark. Results show Vera Rubin NVL72 delivers up to 30x higher throughput per megawatt and 35x lower token costs compared to GB300 NVL72. The tests highlight that agentic sessions involve long-context growth across hundreds of steps, differing significantly from chat or summarization tasks.
Related event: NVIDIA Shows Vera Rubin Silicon: Up to 30x Agent Throughput over GB300(5 posts)→
More from Infra
- SK Hynix ties new US plant to looser chip equipment exports to China, sources say — pstAsiatech · 2026-10-15
- Perplexity's new embedding models: index with a 9B model, search with 0.6B — antoine_chaffin · 2026-10-15
- Unsloth ships GGUF quants for Nemotron 3.5: Bolt-74B runs in 24GB RAM — danielhanchen · 2026-10-15
- vLLM-Omni ships Day-0 serving for FLUX 3 Image Klein with BF16, FP8, NVFP4 support — vllm_project · 2026-10-15
- NVIDIA's Nemotron 3.5 Super VL lands training and inference support on Applied Compute — ypatil125 · 2026-10-15
- CoreWeave bond yield tops 16% as loans outlast customer contracts by ~2 years — tengyanAI · 2026-10-15