{"product_id":"nvidia-699-2g133-0200-c01-a40-48gb-gddr6-300w-dw-fhfl-pcie-4-0-passive-gpu","title":"NVIDIA 699-2G133-0200-C01 A40 48GB GDDR6 300W DW FHFL PCIe 4.0 PASSIVE GPU","description":"\u003cdiv class=\"c4-rich\"\u003e\n\u003cp\u003eThe NVIDIA 699-2G133-0200-C01 is the NVIDIA A40, a data center GPU with 48 GB of GDDR6 memory on a passively cooled, dual-slot, full-height full-length PCIe 4.0 x16 card. It is built on the NVIDIA Ampere architecture GA102 GPU and is used in rack servers for rendering, virtual workstations, and AI and data science workloads that need a large frame buffer.\u003c\/p\u003e\n\u003ch3 style=\"margin:1.4em 0 0.35em\"\u003eAt a glance\u003c\/h3\u003e\n\u003cul\u003e\n\u003cli\u003e48 GB GDDR6 with ECC, 384-bit memory interface\u003c\/li\u003e\n\u003cli\u003ePCIe 4.0 x16, dual-slot FHFL, 300 W passive cooling\u003c\/li\u003e\n\u003cli\u003eOne CPU 8-pin auxiliary power connector\u003c\/li\u003e\n\u003cli\u003eRefurbished, tested twice, 1-year advanced replacement warranty\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003ch3 style=\"margin:1.4em 0 0.35em\"\u003eOutfitting a GPU server?\u003c\/h3\u003e\n\u003cp\u003eNeed more A40 cards than we have listed? Core 4 can source additional quantities and help match power cables and servers to your GPU project. \u003ca href=\"\/pages\/contact?part_number=699-2G133-0200-C01\u0026amp;additional_requirements=Product%3A%20NVIDIA%20699-2G133-0200-C01%20A40%2048GB%20GDDR6%20300W%20DW%20FHFL%20PCIe%204.0%20PASSIVE%20GPU%20%28https%3A%2F%2Fwww.core4solutions.com%2Fproducts%2Fnvidia-699-2g133-0200-c01-a40-48gb-gddr6-300w-dw-fhfl-pcie-4-0-passive-gpu%29\"\u003e\u003cstrong\u003eTalk to a sales engineer\u003c\/strong\u003e\u003c\/a\u003e or call 1-855-55-CORE4.\u003c\/p\u003e\n\u003ch3 style=\"margin:1.4em 0 0.35em\"\u003eTechnical specifications\u003c\/h3\u003e\n\u003ctable style=\"border-collapse:collapse;width:100%;margin:0 0 1em\"\u003e\u003ctbody\u003e\n\u003ctr\u003e\n\u003cth scope=\"row\" style=\"text-align:left;vertical-align:top;font-weight:600;padding:6px 16px 6px 0;border-bottom:1px solid rgba(128,128,128,.2)\"\u003eGPU\u003c\/th\u003e\n\u003ctd style=\"padding:6px 0;border-bottom:1px solid rgba(128,128,128,.2)\"\u003eNVIDIA A40 (GA102-895, Ampere architecture)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003cth scope=\"row\" style=\"text-align:left;vertical-align:top;font-weight:600;padding:6px 16px 6px 0;border-bottom:1px solid rgba(128,128,128,.2)\"\u003eGPU memory\u003c\/th\u003e\n\u003ctd style=\"padding:6px 0;border-bottom:1px solid rgba(128,128,128,.2)\"\u003e48 GB GDDR6, ECC enabled by default\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003cth scope=\"row\" style=\"text-align:left;vertical-align:top;font-weight:600;padding:6px 16px 6px 0;border-bottom:1px solid rgba(128,128,128,.2)\"\u003eMemory interface\u003c\/th\u003e\n\u003ctd style=\"padding:6px 0;border-bottom:1px solid rgba(128,128,128,.2)\"\u003e384-bit, up to 696 GB\/s peak bandwidth\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003cth scope=\"row\" style=\"text-align:left;vertical-align:top;font-weight:600;padding:6px 16px 6px 0;border-bottom:1px solid rgba(128,128,128,.2)\"\u003eGPU clocks\u003c\/th\u003e\n\u003ctd style=\"padding:6px 0;border-bottom:1px solid rgba(128,128,128,.2)\"\u003e1305 MHz base, 1740 MHz boost\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003cth scope=\"row\" style=\"text-align:left;vertical-align:top;font-weight:600;padding:6px 16px 6px 0;border-bottom:1px solid rgba(128,128,128,.2)\"\u003eHost interface\u003c\/th\u003e\n\u003ctd style=\"padding:6px 0;border-bottom:1px solid rgba(128,128,128,.2)\"\u003ePCI Express 4.0 x16\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003cth scope=\"row\" style=\"text-align:left;vertical-align:top;font-weight:600;padding:6px 16px 6px 0;border-bottom:1px solid rgba(128,128,128,.2)\"\u003eTotal board power\u003c\/th\u003e\n\u003ctd style=\"padding:6px 0;border-bottom:1px solid rgba(128,128,128,.2)\"\u003e300 W (default)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003cth scope=\"row\" style=\"text-align:left;vertical-align:top;font-weight:600;padding:6px 16px 6px 0;border-bottom:1px solid rgba(128,128,128,.2)\"\u003eCooling\u003c\/th\u003e\n\u003ctd style=\"padding:6px 0;border-bottom:1px solid rgba(128,128,128,.2)\"\u003ePassive (requires chassis airflow)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003cth scope=\"row\" style=\"text-align:left;vertical-align:top;font-weight:600;padding:6px 16px 6px 0;border-bottom:1px solid rgba(128,128,128,.2)\"\u003eForm factor\u003c\/th\u003e\n\u003ctd style=\"padding:6px 0;border-bottom:1px solid rgba(128,128,128,.2)\"\u003eFull-height, full-length (FHFL), 10.5-inch, dual-slot\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003cth scope=\"row\" style=\"text-align:left;vertical-align:top;font-weight:600;padding:6px 16px 6px 0;border-bottom:1px solid rgba(128,128,128,.2)\"\u003eAuxiliary power\u003c\/th\u003e\n\u003ctd style=\"padding:6px 0;border-bottom:1px solid rgba(128,128,128,.2)\"\u003eOne CPU 8-pin connector\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003cth scope=\"row\" style=\"text-align:left;vertical-align:top;font-weight:600;padding:6px 16px 6px 0;border-bottom:1px solid rgba(128,128,128,.2)\"\u003eVirtualization\u003c\/th\u003e\n\u003ctd style=\"padding:6px 0;border-bottom:1px solid rgba(128,128,128,.2)\"\u003eSR-IOV, 32 virtual functions\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003c\/tbody\u003e\u003c\/table\u003e\n\u003ch3 style=\"margin:1.4em 0 0.35em\"\u003eCompatibility\u003c\/h3\u003e\n\u003cp\u003eThe A40 is designed for servers with a full-height, full-length, dual-slot PCIe slot and the airflow to cool a 300 W passive card. The heatsink has no fan of its own, so it depends on the server's fans pushing air through the card.\u003c\/p\u003e\n\u003cp\u003ePCIe Gen4 x16 is the recommended link. The card also runs at Gen4 x8 and Gen3 x16; Gen3 x8 is not recommended. Auxiliary power comes through a single CPU 8-pin connector, so the server needs a GPU power cable with that pinout.\u003c\/p\u003e\n\u003ch3 style=\"margin:1.4em 0 0.35em\"\u003eCondition\u003c\/h3\u003e\n\u003cp\u003eThis A40 is refurbished: a fully functioning card, tested when it arrives at Core 4 and tested again before it ships. Our refurbished parts come from working production environments that were decommissioned, or from overstock, returns, and off-lease equipment, and the vast majority were never broken or repaired. Anything that does not pass testing is repaired before it is sold.\u003c\/p\u003e\n\u003cp\u003eBecause these cards have already been installed and burned in, early failures have been weeded out, and Core 4 sees a lower dead-on-arrival rate than with new parts straight from the factory. The card is covered by Core 4's 1-year advanced replacement warranty: if it fails within a year, a replacement ships right away, before the failed unit comes back.\u003c\/p\u003e\n\u003ch3 style=\"margin:1.4em 0 0.35em\"\u003eDatasheets and documentation\u003c\/h3\u003e\n\u003cul\u003e\u003cli\u003e\u003ca href=\"https:\/\/www.nvidia.com\/content\/dam\/en-zz\/Solutions\/Data-Center\/a40\/NVIDIA%20A40%20Product%20Brief.pdf\" target=\"_blank\" rel=\"noopener\"\u003eNVIDIA A40 Product Brief (PB-09976-001_v08)\u003c\/a\u003e\u003c\/li\u003e\u003c\/ul\u003e\n\u003ch3 style=\"margin:1.4em 0 0.35em\"\u003eCommon questions\u003c\/h3\u003e\n\u003cp\u003e\u003cstrong\u003eWhat power cable does the A40 use?\u003c\/strong\u003e The A40 takes one CPU 8-pin auxiliary power connector, not a standard PCIe 8-pin graphics connector. Use a GPU power cable made for the server that supplies the CPU 8-pin pinout.\u003c\/p\u003e\n\u003cp\u003e\u003cstrong\u003eWill the A40 run in a PCIe Gen3 slot?\u003c\/strong\u003e Yes. Gen3 x16 is a supported link, as is Gen4 x8. Gen4 x16 is recommended for full bandwidth, and Gen3 x8 is not recommended.\u003c\/p\u003e\n\u003cp\u003e\u003cstrong\u003eCan I use a passive A40 in a desktop workstation?\u003c\/strong\u003e The card has no onboard fan and relies on directed airflow from the chassis, which rack servers built for passive GPUs provide. A typical desktop tower does not move enough air through the heatsink to cool a 300 W passive card.\u003c\/p\u003e\n\u003cp\u003e\u003cstrong\u003eDoes the A40 output video?\u003c\/strong\u003e It ships in Display Off mode by default for compute and virtualization use. NVIDIA also defines Display On operating modes with 8 GB or 256 MB BAR1, which can be selected when display output is needed.\u003c\/p\u003e\n\u003c\/div\u003e","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":67907284238571,"sku":"nvidia 699-2g133-0200-c01 refurbished","price":4499.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0843\/8769\/2779\/files\/699-2G133-0200-C01.jpg?v=1793757620","url":"https:\/\/www.core4solutions.com\/products\/nvidia-699-2g133-0200-c01-a40-48gb-gddr6-300w-dw-fhfl-pcie-4-0-passive-gpu","provider":"Core 4 Solutions","version":"1.0","type":"link"}