ChipsSep 17, 2026 · 06:561 source
Nvidia Rubin NVL72 Delivers 67x Throughput Per Cost in SemiAnalysis Test Beating Company Claims
From marketbrief.now
SemiAnalysis testing found the Nvidia Rubin NVL72 delivers 67 times the total throughput per total cost of ownership compared to the GB300 Dynamo at 170 tokens per second, exceeding the 3x gain announced at GTC 2026. The system uses TRTLLM NVFP4 Dense and was evaluated with the open source InferenceX v3 tool. The platform's gains come from a co-design of six products including the Rubin GPU, Vera CPU, and NVLink 6 Switch. SemiAnalysis spent $3 million developing InferenceX v3 and the AgentX benchmark. Some critics say the 67x figure applies only to the 170 tokens per second setting.
Read the sourceSign in to suggest
Sources
#nvidia#rubin-nvl72#gpu-performance#semianalysis#throughput-cost#rubin#nvl72#throughputMarkdown
Content history (2)
- 2026-10-16 · Summary · vi · Replaced stored textTủ AI mới nhất từ nhà sản xuất chip cho thấy tăng trưởng hiệu suất 7 lần trên mỗi watt so…
- 2026-10-16 · Title · vi · Replaced stored textNvidia Rubin NVL72 đạt 67x thông lượng trên chi phí trong bài kiểm tra SemiAnalysis, vượt…Nvidia Rubin NVL72 đạt 67x throughput trên SemiAnalysis, vượt qua dự báo công ty
One ranked edition, every morning
The stories that matter today. Free, cancel anytime.
Telegram @aidr_today