{"product_id":"ng3py-refurbished-dell-nvidia-l4-24gb-passive-gpu","title":"NG3PY - Refurbished - Dell NVIDIA L4 24GB Passive GPU","description":"\u003cp\u003eCondition - Refurbished\u003c\/p\u003e\n\u003cp\u003e\u003cstrong data-end=\"39\" data-start=\"4\"\u003eDell NVIDIA L4 24GB Passive GPU\u003c\/strong\u003e (Dell Part Number: \u003cstrong data-end=\"68\" data-start=\"59\"\u003eNG3PY\u003c\/strong\u003e) is a high-efficiency, low-profile accelerator designed for AI inference, video processing, virtual desktops, and graphics-intensive workloads. Powered by NVIDIA’s Ada Lovelace architecture, it offers significant performance improvements over its predecessor, the T4, while maintaining a compact and energy-efficient design.\u003c\/p\u003e\n\u003ch3 data-start=\"133\" data-end=\"158\" class=\"\"\u003eSpecifications\u003c\/h3\u003e\n\u003cul data-start=\"160\" data-end=\"877\"\u003e\n\u003cli data-start=\"160\" data-end=\"221\" class=\"\"\u003e\n\u003cp data-start=\"162\" data-end=\"221\" class=\"\"\u003e\u003cstrong data-start=\"162\" data-end=\"182\"\u003eGPU Architecture\u003c\/strong\u003e: \u003cspan class=\"relative -mx-px my-[-0.2rem] rounded px-px py-[0.2rem] transition-colors duration-100 ease-in-out\"\u003eNVIDIA Ada Lovelace\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/li\u003e\n\u003cli data-start=\"222\" data-end=\"277\" class=\"\"\u003e\n\u003cp data-start=\"224\" data-end=\"277\" class=\"\"\u003e\u003cstrong data-start=\"224\" data-end=\"238\"\u003eCUDA Cores\u003c\/strong\u003e: \u003cspan class=\"relative -mx-px my-[-0.2rem] rounded px-px py-[0.2rem] transition-colors duration-100 ease-in-out\"\u003e7,424\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/li\u003e\n\u003cli data-start=\"278\" data-end=\"335\" class=\"\"\u003e\n\u003cp data-start=\"280\" data-end=\"335\" class=\"\"\u003e\u003cstrong data-start=\"280\" data-end=\"296\"\u003eTensor Cores\u003c\/strong\u003e: \u003cspan class=\"relative -mx-px my-[-0.2rem] rounded px-px py-[0.2rem] transition-colors duration-100 ease-in-out\"\u003e232 (4th generation)\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/li\u003e\n\u003cli data-start=\"336\" data-end=\"389\" class=\"\"\u003e\n\u003cp data-start=\"338\" data-end=\"389\" class=\"\"\u003e\u003cstrong data-start=\"338\" data-end=\"350\"\u003eRT Cores\u003c\/strong\u003e: \u003cspan class=\"relative -mx-px my-[-0.2rem] rounded px-px py-[0.2rem] transition-colors duration-100 ease-in-out\"\u003e58 (3rd generation)\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/li\u003e\n\u003cli data-start=\"390\" data-end=\"445\" class=\"\"\u003e\n\u003cp data-start=\"392\" data-end=\"445\" class=\"\"\u003e\u003cstrong data-start=\"392\" data-end=\"406\"\u003eGPU Memory\u003c\/strong\u003e: \u003cspan class=\"relative -mx-px my-[-0.2rem] rounded px-px py-[0.2rem] transition-colors duration-100 ease-in-out\"\u003e24 GB GDDR6 with ECC\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/li\u003e\n\u003cli data-start=\"446\" data-end=\"507\" class=\"\"\u003e\n\u003cp data-start=\"448\" data-end=\"507\" class=\"\"\u003e\u003cstrong data-start=\"448\" data-end=\"468\"\u003eMemory Bandwidth\u003c\/strong\u003e: \u003cspan class=\"relative -mx-px my-[-0.2rem] rounded px-px py-[0.2rem] transition-colors duration-100 ease-in-out\"\u003e300 GB\/s\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/li\u003e\n\u003cli data-start=\"508\" data-end=\"562\" class=\"\"\u003e\n\u003cp data-start=\"510\" data-end=\"562\" class=\"\"\u003e\u003cstrong data-start=\"510\" data-end=\"523\"\u003eInterface\u003c\/strong\u003e: \u003cspan class=\"relative -mx-px my-[-0.2rem] rounded px-px py-[0.2rem] transition-colors duration-100 ease-in-out\"\u003ePCIe Gen 4.0 x16\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/li\u003e\n\u003cli data-start=\"563\" data-end=\"621\" class=\"\"\u003e\n\u003cp data-start=\"565\" data-end=\"621\" class=\"\"\u003e\u003cstrong data-start=\"565\" data-end=\"580\"\u003eForm Factor\u003c\/strong\u003e: \u003cspan class=\"relative -mx-px my-[-0.2rem] rounded px-px py-[0.2rem] transition-colors duration-100 ease-in-out\"\u003eLow-profile, single-slot (169 mm x 69 mm)\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/li\u003e\n\u003cli data-start=\"622\" data-end=\"676\" class=\"\"\u003e\n\u003cp data-start=\"624\" data-end=\"676\" class=\"\"\u003e\u003cstrong data-start=\"624\" data-end=\"635\"\u003eCooling\u003c\/strong\u003e: \u003cspan class=\"relative -mx-px my-[-0.2rem] rounded px-px py-[0.2rem] transition-colors duration-100 ease-in-out\"\u003ePassive (requires adequate system airflow)\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/li\u003e\n\u003cli data-start=\"677\" data-end=\"741\" class=\"\"\u003e\n\u003cp data-start=\"679\" data-end=\"741\" class=\"\"\u003e\u003cstrong data-start=\"679\" data-end=\"700\"\u003ePower Consumption\u003c\/strong\u003e: \u003cspan class=\"relative -mx-px my-[-0.2rem] rounded px-px py-[0.2rem] transition-colors duration-100 ease-in-out\"\u003e72W (no external power connector required)\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/li\u003e\n\u003cli data-start=\"742\" data-end=\"769\" class=\"\"\u003e\n\u003cp data-start=\"744\" data-end=\"769\" class=\"\"\u003e\u003cstrong data-start=\"744\" data-end=\"763\"\u003eDisplay Outputs\u003c\/strong\u003e: None\u003c\/p\u003e\n\u003c\/li\u003e\n\u003cli data-start=\"770\" data-end=\"877\" class=\"\"\u003e\n\u003cp data-start=\"772\" data-end=\"877\" class=\"\"\u003e\u003cstrong data-start=\"772\" data-end=\"790\"\u003eSupported APIs\u003c\/strong\u003e: \u003cspan class=\"relative -mx-px my-[-0.2rem] rounded px-px py-[0.2rem] transition-colors duration-100 ease-in-out\"\u003eDirectX 12 Ultimate, Shader Model 6.6, OpenGL 4.6, Vulkan 1.3, CUDA 12.0, OpenCL 3.0\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003ch3 data-start=\"884\" data-end=\"913\" class=\"\"\u003ePerformance Highlights\u003c\/h3\u003e\n\u003cul data-start=\"915\" data-end=\"1307\"\u003e\n\u003cli data-start=\"915\" data-end=\"985\" class=\"\"\u003e\n\u003cp data-start=\"917\" data-end=\"985\" class=\"\"\u003e\u003cstrong data-start=\"917\" data-end=\"944\"\u003eFP32 (Single Precision)\u003c\/strong\u003e: \u003cspan class=\"relative -mx-px my-[-0.2rem] rounded px-px py-[0.2rem] transition-colors duration-100 ease-in-out\"\u003e30.3 TFLOPS\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/li\u003e\n\u003cli data-start=\"986\" data-end=\"1056\" class=\"\"\u003e\n\u003cp data-start=\"988\" data-end=\"1056\" class=\"\"\u003e\u003cstrong data-start=\"988\" data-end=\"1015\"\u003eTF32 Tensor Performance\u003c\/strong\u003e: \u003cspan class=\"relative -mx-px my-[-0.2rem] rounded px-px py-[0.2rem] transition-colors duration-100 ease-in-out\"\u003e60 TFLOPS (up to 120 TFLOPS with sparsity)\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/li\u003e\n\u003cli data-start=\"1057\" data-end=\"1127\" class=\"\"\u003e\n\u003cp data-start=\"1059\" data-end=\"1127\" class=\"\"\u003e\u003cstrong data-start=\"1059\" data-end=\"1086\"\u003eFP16 Tensor Performance\u003c\/strong\u003e: \u003cspan class=\"relative -mx-px my-[-0.2rem] rounded px-px py-[0.2rem] transition-colors duration-100 ease-in-out\"\u003e121 TFLOPS (up to 242 TFLOPS with sparsity)\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/li\u003e\n\u003cli data-start=\"1128\" data-end=\"1197\" class=\"\"\u003e\n\u003cp data-start=\"1130\" data-end=\"1197\" class=\"\"\u003e\u003cstrong data-start=\"1130\" data-end=\"1156\"\u003eFP8 Tensor Performance\u003c\/strong\u003e: \u003cspan class=\"relative -mx-px my-[-0.2rem] rounded px-px py-[0.2rem] transition-colors duration-100 ease-in-out\"\u003e242.5 TFLOPS (up to 485 TFLOPS with sparsity)\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/li\u003e\n\u003cli data-start=\"1198\" data-end=\"1307\" class=\"\"\u003e\n\u003cp data-start=\"1200\" data-end=\"1307\" class=\"\"\u003e\u003cstrong data-start=\"1200\" data-end=\"1220\"\u003eINT8 Performance\u003c\/strong\u003e: \u003cspan class=\"relative -mx-px my-[-0.2rem] rounded px-px py-[0.2rem] transition-colors duration-100 ease-in-out\"\u003e242.5 TOPS (up to 485 TOPS with sparsity)\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003ch3 data-start=\"1401\" data-end=\"1435\" class=\"\"\u003eCompatibility \u0026amp; Deployment\u003c\/h3\u003e\n\u003cp data-start=\"1437\" data-end=\"1602\" class=\"\"\u003e\u003cspan class=\"relative -mx-px my-[-0.2rem] rounded px-px py-[0.2rem] transition-colors duration-100 ease-in-out\"\u003eThe L4's low-profile, single-slot design and passive cooling make it ideal for dense server environments.\u003c\/span\u003e \u003cspan class=\"relative -mx-px my-[-0.2rem] rounded px-px py-[0.2rem] transition-colors duration-100 ease-in-out\"\u003eIt is compatible with systems that have a PCIe Gen 4.0 x16 slot and sufficient airflow.\u003c\/span\u003e \u003cspan class=\"relative -mx-px my-[-0.2rem] rounded px-px py-[0.2rem] transition-colors duration-100 ease-in-out\"\u003eThe absence of external power connectors simplifies integration into existing infrastructures.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e \u003c\/p\u003e","brand":"ShopITgear","offers":[{"title":"Default Title","offer_id":47923363119204,"sku":null,"price":4290.45,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0767\/3482\/4548\/files\/NG3PY.jpg?v=1771296043","url":"https:\/\/resilient-tec.com\/products\/ng3py-refurbished-dell-nvidia-l4-24gb-passive-gpu","provider":"Resilient Tec, LLC","version":"1.0","type":"link"}