{"product_id":"k-node-v100-16x-sxm3-512gb","title":"Kentino AI Node V100 HGX-2 — 16× NVIDIA V100 SXM3 32 GB, 512 GB HBM2","description":"\u003cdiv style=\"font-family: -apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,sans-serif; line-height: 1.7; color: #1a1a1a;\"\u003e\n\u003c!-- IMAGE PLACEHOLDER 1: 10U node front, white background --\u003e \u003c!-- IMAGE PLACEHOLDER 2: HGX-2 baseboard, 16 SXM3 modules + NVSwitch --\u003e \u003c!-- IMAGE PLACEHOLDER 3: refurbishment bench - thermal pad renewal --\u003e \u003c!-- IMAGE PLACEHOLDER 4: rack-installed, 10U footprint visible --\u003e\n\u003cdiv style=\"background: linear-gradient(135deg,#0d0d0d 0%,#1a1a2e 100%); color: #fff; padding: 32px; border-radius: 12px; margin-bottom: 32px;\"\u003e\n\u003cp style=\"font-size: 18px; margin: 0 0 20px 0; color: #ccc;\"\u003eKentino AI Node V100 HGX-2\u003c\/p\u003e\n\u003cp style=\"font-size: 28px; font-weight: bold; margin: 0 0 16px 0; line-height: 1.3;\"\u003e512 GB HBM2, Sixteen GPUs, Full NVSwitch\u003cbr\u003e16x V100 SXM3 32 GB | 124.8 TFLOPS FP64\u003c\/p\u003e\n\u003cdiv style=\"display: flex; gap: 16px; flex-wrap: wrap; margin-top: 24px;\"\u003e\n\u003cdiv style=\"background: rgba(51,79,180,0.12); border: 1px solid #334fb4; border-radius: 8px; padding: 14px 16px; text-align: center; flex: 1; min-width: 110px;\"\u003e\n\u003cdiv style=\"font-size: 24px; font-weight: 800; color: #334fb4;\"\u003e512 GB\u003c\/div\u003e\n\u003cdiv style=\"font-size: 11px; color: #555; text-transform: uppercase; letter-spacing: 1px;\"\u003eHBM2 pool\u003c\/div\u003e\n\u003c\/div\u003e\n\u003cdiv style=\"background: rgba(51,79,180,0.12); border: 1px solid #334fb4; border-radius: 8px; padding: 14px 16px; text-align: center; flex: 1; min-width: 110px;\"\u003e\n\u003cdiv style=\"font-size: 24px; font-weight: 800; color: #334fb4;\"\u003e16\u003c\/div\u003e\n\u003cdiv style=\"font-size: 11px; color: #555; text-transform: uppercase; letter-spacing: 1px;\"\u003eGPUs, any-to-any\u003c\/div\u003e\n\u003c\/div\u003e\n\u003cdiv style=\"background: rgba(51,79,180,0.12); border: 1px solid #334fb4; border-radius: 8px; padding: 14px 16px; text-align: center; flex: 1; min-width: 110px;\"\u003e\n\u003cdiv style=\"font-size: 24px; font-weight: 800; color: #334fb4;\"\u003e124.8\u003c\/div\u003e\n\u003cdiv style=\"font-size: 11px; color: #555; text-transform: uppercase; letter-spacing: 1px;\"\u003eTFLOPS FP64\u003c\/div\u003e\n\u003c\/div\u003e\n\u003cdiv style=\"background: rgba(51,79,180,0.12); border: 1px solid #334fb4; border-radius: 8px; padding: 14px 16px; text-align: center; flex: 1; min-width: 110px;\"\u003e\n\u003cdiv style=\"font-size: 24px; font-weight: 800; color: #334fb4;\"\u003eNo KYC\u003c\/div\u003e\n\u003cdiv style=\"font-size: 11px; color: #555; text-transform: uppercase; letter-spacing: 1px;\"\u003enot export-controlled\u003c\/div\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e\n\u003cp style=\"margin-top: 20px; font-size: 15px; color: #aaa;\"\u003eThe DGX-2 class machine. Built to order on a Supermicro host.\u003c\/p\u003e\n\u003c\/div\u003e\n\u003cp style=\"font-size: 17px; color: #333; margin-bottom: 24px;\"\u003eA 10U node carrying sixteen NVIDIA V100 SXM3 modules on an HGX-2 baseboard with full NVSwitch any-to-any connectivity: 512 GB of HBM2, 124.8 TFLOPS of FP64, and every GPU talking to every other at full bandwidth. We build these to order on a Supermicro SYS-9029GP-TNVRT host. It is the cheapest route we know to a half-terabyte NVSwitch-pooled VRAM space, and for double-precision HPC it remains a serious tool.\u003c\/p\u003e\n\u003ch2 style=\"font-size: 22px; font-weight: bold; margin: 40px 0 16px 0; padding-bottom: 8px; border-bottom: 3px solid #334fb4;\"\u003eHardware\u003c\/h2\u003e\n\u003ctable style=\"width: 100%; border-collapse: collapse; margin-bottom: 24px; font-size: 15px;\"\u003e\n\u003cthead\u003e\n\u003ctr style=\"background: #0d0d0d; color: #fff;\"\u003e\n\u003cth style=\"padding: 12px 16px; text-align: left;\"\u003eComponent\u003c\/th\u003e\n\u003cth style=\"padding: 12px 16px; text-align: left;\"\u003eDetail\u003c\/th\u003e\n\u003c\/tr\u003e\n\u003c\/thead\u003e\n\u003ctbody\u003e\n\u003ctr style=\"background: #f8f8f8;\"\u003e\n\u003ctd style=\"padding: 10px 16px; font-weight: 600;\"\u003eGPUs\u003c\/td\u003e\n\u003ctd style=\"padding: 10px 16px;\"\u003e16x NVIDIA V100 SXM3 32 GB HBM2 (Volta, 350 W per module)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"padding: 10px 16px; font-weight: 600;\"\u003eVRAM pool\u003c\/td\u003e\n\u003ctd style=\"padding: 10px 16px;\"\u003e512 GB HBM2, NVSwitch-pooled as one address space\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"background: #f8f8f8;\"\u003e\n\u003ctd style=\"padding: 10px 16px; font-weight: 600;\"\u003eMemory bandwidth\u003c\/td\u003e\n\u003ctd style=\"padding: 10px 16px;\"\u003e900 GB\/s per GPU\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"padding: 10px 16px; font-weight: 600;\"\u003eGPU interconnect\u003c\/td\u003e\n\u003ctd style=\"padding: 10px 16px;\"\u003eNVLink 2 via NVSwitch - full any-to-any across all 16 GPUs\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"background: #f8f8f8;\"\u003e\n\u003ctd style=\"padding: 10px 16px; font-weight: 600;\"\u003eCompute\u003c\/td\u003e\n\u003ctd style=\"padding: 10px 16px;\"\u003e2,000 TFLOPS fp16 | 124.8 TFLOPS FP64\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"padding: 10px 16px; font-weight: 600;\"\u003eHost\u003c\/td\u003e\n\u003ctd style=\"padding: 10px 16px;\"\u003eSupermicro SYS-9029GP-TNVRT, 10U\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"background: #f8f8f8;\"\u003e\n\u003ctd style=\"padding: 10px 16px; font-weight: 600;\"\u003eCPUs\u003c\/td\u003e\n\u003ctd style=\"padding: 10px 16px;\"\u003e2x Intel Xeon Scalable, dual LGA3647\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"padding: 10px 16px; font-weight: 600;\"\u003eSystem memory\u003c\/td\u003e\n\u003ctd style=\"padding: 10px 16px;\"\u003e1.5 TB DDR4-2666 ECC RDIMM (24x 64 GB, all slots populated)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"background: #f8f8f8;\"\u003e\n\u003ctd style=\"padding: 10px 16px; font-weight: 600;\"\u003eStorage\u003c\/td\u003e\n\u003ctd style=\"padding: 10px 16px;\"\u003e2x 1.92 TB U.2 NVMe boot + 2x 3.84 TB U.2 NVMe data. Expandable\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"padding: 10px 16px; font-weight: 600;\"\u003eNetworking\u003c\/td\u003e\n\u003ctd style=\"padding: 10px 16px;\"\u003e2x dual-port 100 GbE\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"background: #f8f8f8;\"\u003e\n\u003ctd style=\"padding: 10px 16px; font-weight: 600;\"\u003ePower\u003c\/td\u003e\n\u003ctd style=\"padding: 10px 16px;\"\u003e~6.6 kW sustained, redundant PSU\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"padding: 10px 16px; font-weight: 600;\"\u003eBuild\u003c\/td\u003e\n\u003ctd style=\"padding: 10px 16px;\"\u003eAssembled, burned in and memtested by Kentino with a written report\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003c\/tbody\u003e\n\u003c\/table\u003e\n\u003ch2 style=\"font-size: 22px; font-weight: bold; margin: 40px 0 16px 0; padding-bottom: 8px; border-bottom: 3px solid #334fb4;\"\u003eWhat it runs\u003c\/h2\u003e\n\u003cp\u003eVolta is fp16 and FP64 hardware. These are the workloads it is genuinely good at.\u003c\/p\u003e\n\u003ctable style=\"width: 100%; border-collapse: collapse; margin-bottom: 24px; font-size: 15px;\"\u003e\n\u003cthead\u003e\n\u003ctr style=\"background: #0d0d0d; color: #fff;\"\u003e\n\u003cth style=\"padding: 12px 16px; text-align: left;\"\u003eComponent\u003c\/th\u003e\n\u003cth style=\"padding: 12px 16px; text-align: left;\"\u003eDetail\u003c\/th\u003e\n\u003c\/tr\u003e\n\u003c\/thead\u003e\n\u003ctbody\u003e\n\u003ctr style=\"background: #f8f8f8;\"\u003e\n\u003ctd style=\"padding: 10px 16px; font-weight: 600;\"\u003eDouble-precision HPC\u003c\/td\u003e\n\u003ctd style=\"padding: 10px 16px;\"\u003eCFD, FEA, molecular dynamics, climate - 124.8 TFLOPS FP64 per node\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"padding: 10px 16px; font-weight: 600;\"\u003efp16 training, validated codes\u003c\/td\u003e\n\u003ctd style=\"padding: 10px 16px;\"\u003earchitectures already tuned for Volta\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"background: #f8f8f8;\"\u003e\n\u003ctd style=\"padding: 10px 16px; font-weight: 600;\"\u003eLarge-pool experiments\u003c\/td\u003e\n\u003ctd style=\"padding: 10px 16px;\"\u003e512 GB NVSwitch-coherent VRAM where capacity matters more than speed\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"padding: 10px 16px; font-weight: 600;\"\u003eTeaching and research\u003c\/td\u003e\n\u003ctd style=\"padding: 10px 16px;\"\u003ereal 16-GPU NVSwitch behaviour on a fixed grant budget\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"background: #f8f8f8;\"\u003e\n\u003ctd style=\"padding: 10px 16px; font-weight: 600;\"\u003eDGX-2 \/ HGX-2 estate expansion\u003c\/td\u003e\n\u003ctd style=\"padding: 10px 16px;\"\u003enode parity with Volta hardware you already run\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003c\/tbody\u003e\n\u003c\/table\u003e\n\u003cp style=\"font-size: 14px; color: #666;\"\u003e\u003cem\u003eThroughput figures are published vendor specifications for this GPU generation, not measurements on this exact configuration. We will give you measured numbers for your workload before you commit.\u003c\/em\u003e\u003c\/p\u003e\n\u003ch2 style=\"font-size: 22px; font-weight: bold; margin: 40px 0 16px 0; padding-bottom: 8px; border-bottom: 3px solid #334fb4;\"\u003ePower and cooling\u003c\/h2\u003e\n\u003cp\u003eSixteen modules at 350 W is 5.6 kW of GPU - the same wall draw as an eight-GPU Hopper node, for a fraction of the throughput. Budget a dedicated 32 A three-phase feed and roughly one node per 10 kW of rack. The 10U chassis also takes a quarter of a standard rack. It needs genuine datacentre front-to-back airflow and a contained cold aisle below 24 C for 24\/7 operation.\u003c\/p\u003e\n\u003ch2 style=\"font-size: 22px; font-weight: bold; margin: 40px 0 16px 0; padding-bottom: 8px; border-bottom: 3px solid #334fb4;\"\u003eBe clear about what this is\u003c\/h2\u003e\n\u003cp\u003e\u003cstrong\u003eNo bf16, no fp8, no INT8 tensor cores.\u003c\/strong\u003e Volta has none of them. Most current quantised inference stacks assume bf16 or better, so a large part of today's ecosystem either will not run or will run badly here. 512 GB sounds competitive against a newer node, but the pool is HBM2 at 900 GB\/s with fp16-only tensor paths. Do not buy this as an LLM serving node on the capacity number alone - if that is your workload, ask us about the A100 node instead.\u003c\/p\u003e\n\u003cp\u003e\u003cstrong\u003eBuilt from sourced baseboards.\u003c\/strong\u003e There is no new-channel supply of HGX-2 baseboards. We source them, and if they are ex-datacentre every module gets fresh thermal pads and paste plus a 72 hour burn-in before it ships - degraded factory pads are the main failure mode on hardware of this age. Lead time depends on sourcing and we will give you a real date, not an optimistic one.\u003c\/p\u003e\n\u003cp\u003e\u003cstrong\u003eOne genuine advantage:\u003c\/strong\u003e V100 predates the Advanced Computing Item thresholds, so there is \u003cstrong\u003eno KYC form and no End User Certificate\u003c\/strong\u003e. If export paperwork is what is blocking you on newer hardware, this is the node that does not need it.\u003c\/p\u003e\n\u003ch2 style=\"font-size: 22px; font-weight: bold; margin: 40px 0 16px 0; padding-bottom: 8px; border-bottom: 3px solid #334fb4;\"\u003eWhat you get from Kentino\u003c\/h2\u003e\n\u003cp\u003eWe build, test and support the complete node: host selection, assembly, thermal work on the baseboard, burn-in with a written report, OS and driver stack pinned to a Volta-compatible CUDA version, rack and airflow guidance, EU-based logistics and warranty.\u003c\/p\u003e\n\u003cp\u003e\u003cem\u003ePriced on request. Tell us your workload and we will come back with a firm quote, a realistic lead time, and an honest view of whether this or a newer node is the better buy.\u003c\/em\u003e\u003c\/p\u003e\n\u003c\/div\u003e","brand":"Kentino","offers":[{"title":"Default Title","offer_id":54417335877960,"sku":null,"price":0.0,"currency_code":"EUR","in_stock":true}],"url":"https:\/\/kentino.com\/de\/products\/k-node-v100-16x-sxm3-512gb","provider":"Kentino","version":"1.0","type":"link"}