{"id":9644217401602,"title":"HP ZGX Fury G1n GB300 AI Workstation","handle":"hp-zgx-fury-g1n-gb300-ai-workstation","description":"\u003cp style=\"margin:1em 0\"\u003eThe HP ZGX Fury G1n is an enterprise desktop AI supercomputer built around the NVIDIA Grace Blackwell Ultra (GB300) Superchip. Delivering up to 20 PFLOPS of FP4 AI compute, it accelerates training, fine-tuning, and deployment of large language models up to 1 trillion parameters, AI agents, and scientific simulations within a local infrastructure.\u003c\/p\u003e\u003cp style=\"margin:1em 0\"\u003eEquipped with 748 GB of coherent unified memory combining 252 GB HBM3e GPU memory at 7.1 TB\/s and 496 GB LPDDR5X CPU memory linked via NVLink-C2C at 900 GB\/s, this workstation enables low-latency data throughput for complex retrieval-augmented generation and digital twin workloads.\u003c\/p\u003e\u003cp style=\"margin:1em 0\"\u003ePowered by a 72-core NVIDIA Grace Arm Neoverse V2 CPU alongside dual 400 GbE QSFP NVIDIA ConnectX-8 SuperNIC networking, the ZGX Fury G1n provides high-throughput clustering capabilities and datacentre-class cooling designed for continuous 24\/7 workstation operation without specialized liquid racks.\u003c\/p\u003e\n\u003ctable class=\"pu-table\" style=\"width:100%;border-collapse:separate;border-spacing:0;border:0;box-shadow:none;outline:none;background:none;table-layout:fixed;margin:0 0 1em\"\u003e\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd style=\"border:0;padding:0.4em 0.75em 0.4em 0;opacity:0.65;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003eBrand\u003c\/td\u003e\n\u003ctd style=\"border:0;padding:0.4em 0;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003eHP\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"border:0;padding:0.4em 0.75em 0.4em 0;opacity:0.65;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003eModel\u003c\/td\u003e\n\u003ctd style=\"border:0;padding:0.4em 0;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003eHP ZGX Fury G1n\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"border:0;padding:0.4em 0.75em 0.4em 0;opacity:0.65;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003eProduct Type\u003c\/td\u003e\n\u003ctd style=\"border:0;padding:0.4em 0;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003eEnterprise Desktop AI Supercomputer \/ AI Workstation\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"border:0;padding:0.4em 0.75em 0.4em 0;opacity:0.65;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003eProcessor Platform\u003c\/td\u003e\n\u003ctd style=\"border:0;padding:0.4em 0;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003eNVIDIA GB300 Grace Blackwell Ultra Superchip\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"border:0;padding:0.4em 0.75em 0.4em 0;opacity:0.65;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003eCPU\u003c\/td\u003e\n\u003ctd style=\"border:0;padding:0.4em 0;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003e1 × NVIDIA Grace (72-Core Arm Neoverse V2)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"border:0;padding:0.4em 0.75em 0.4em 0;opacity:0.65;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003eGPU\u003c\/td\u003e\n\u003ctd style=\"border:0;padding:0.4em 0;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003e1 × NVIDIA Blackwell Ultra\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"border:0;padding:0.4em 0.75em 0.4em 0;opacity:0.65;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003eTotal Coherent Memory\u003c\/td\u003e\n\u003ctd style=\"border:0;padding:0.4em 0;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003e748 GB Unified\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"border:0;padding:0.4em 0.75em 0.4em 0;opacity:0.65;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003eGPU Memory\u003c\/td\u003e\n\u003ctd style=\"border:0;padding:0.4em 0;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003e252 GB HBM3e, 7.1 TB\/s\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"border:0;padding:0.4em 0.75em 0.4em 0;opacity:0.65;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003eCPU Memory\u003c\/td\u003e\n\u003ctd style=\"border:0;padding:0.4em 0;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003e496 GB LPDDR5X, 396 GB\/s\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"border:0;padding:0.4em 0.75em 0.4em 0;opacity:0.65;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003eInterconnect\u003c\/td\u003e\n\u003ctd style=\"border:0;padding:0.4em 0;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003eNVLink-C2C (900 GB\/s)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"border:0;padding:0.4em 0.75em 0.4em 0;opacity:0.65;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003eAI Performance\u003c\/td\u003e\n\u003ctd style=\"border:0;padding:0.4em 0;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003eUp to 20 PFLOPS FP4 Tensor Core\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"border:0;padding:0.4em 0.75em 0.4em 0;opacity:0.65;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003eModel Support\u003c\/td\u003e\n\u003ctd style=\"border:0;padding:0.4em 0;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003eUp to 1 Trillion Parameters\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"border:0;padding:0.4em 0.75em 0.4em 0;opacity:0.65;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003eGPU Partitioning\u003c\/td\u003e\n\u003ctd style=\"border:0;padding:0.4em 0;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003eMulti-Instance GPU (MIG) Up to 7 Instances\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"border:0;padding:0.4em 0.75em 0.4em 0;opacity:0.65;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003eNetworking\u003c\/td\u003e\n\u003ctd style=\"border:0;padding:0.4em 0;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003eNVIDIA ConnectX-8 (Up to 800 Gb\/s Ethernet, 2 × QSFP 400 Gb\/s)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"border:0;padding:0.4em 0.75em 0.4em 0;opacity:0.65;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003eStandard Ethernet\u003c\/td\u003e\n\u003ctd style=\"border:0;padding:0.4em 0;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003e10 GbE + 1 GbE Management\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"border:0;padding:0.4em 0.75em 0.4em 0;opacity:0.65;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003eStorage Interface\u003c\/td\u003e\n\u003ctd style=\"border:0;padding:0.4em 0;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003eM.2 Gen 5 Platform Slots\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"border:0;padding:0.4em 0.75em 0.4em 0;opacity:0.65;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003eOperating System\u003c\/td\u003e\n\u003ctd style=\"border:0;padding:0.4em 0;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003eUbuntu with NVIDIA AI Developer Tools (DGX Software Stack)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"border:0;padding:0.4em 0.75em 0.4em 0;opacity:0.65;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003ePower Supply\u003c\/td\u003e\n\u003ctd style=\"border:0;padding:0.4em 0;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003eHP Enterprise High-Efficiency Power Supply (~1,600 W Platform)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"border:0;padding:0.4em 0.75em 0.4em 0;opacity:0.65;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003eCooling\u003c\/td\u003e\n\u003ctd style=\"border:0;padding:0.4em 0;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003eDatacentre-Class Component Cooling\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"border:0;padding:0.4em 0.75em 0.4em 0;opacity:0.65;vertical-align:top\"\u003eWeight\u003c\/td\u003e\n\u003ctd style=\"border:0;padding:0.4em 0;vertical-align:top\"\u003e24.5 kg\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003c\/tbody\u003e\u003c\/table\u003e","published_at":"2026-09-21T21:55:14+08:00","created_at":"2026-09-21T21:55:08+08:00","vendor":"HP","type":"","tags":["AI Workstation","Created by Product Upload","Desktop AI Supercomputer","Grace Blackwell Ultra","HP Workstation","HP ZGX Fury G1n","NVIDIA ConnectX-8","NVIDIA GB300"],"price":14306859,"price_min":14306859,"price_max":15565854,"available":true,"price_varies":true,"compare_at_price":17168231,"compare_at_price_min":17168231,"compare_at_price_max":18679025,"compare_at_price_varies":true,"variants":[{"id":48537000182018,"title":"RTX PRO 2000 Blackwell \/ 4x2TB","option1":"RTX PRO 2000 Blackwell \/ 4x2TB","option2":null,"option3":null,"sku":"E6ZS0PT","requires_shipping":true,"taxable":true,"featured_image":null,"available":true,"name":"HP ZGX Fury G1n GB300 AI Workstation - RTX PRO 2000 Blackwell \/ 4x2TB","public_title":"RTX PRO 2000 Blackwell \/ 4x2TB","options":["RTX PRO 2000 Blackwell \/ 4x2TB"],"price":15222434,"weight":5000,"compare_at_price":18266921,"inventory_management":null,"barcode":"199764756268","requires_selling_plan":false,"selling_plan_allocations":[],"quantity_rule":{"min":1,"max":null,"increment":1}},{"id":48537000214786,"title":"RTX PRO 4000 Blackwell \/ 2x2TB + 2x4TB","option1":"RTX PRO 4000 Blackwell \/ 2x2TB + 2x4TB","option2":null,"option3":null,"sku":"E6ZS5PT","requires_shipping":true,"taxable":true,"featured_image":null,"available":true,"name":"HP ZGX Fury G1n GB300 AI Workstation - RTX PRO 4000 Blackwell \/ 2x2TB + 2x4TB","public_title":"RTX PRO 4000 Blackwell \/ 2x2TB + 2x4TB","options":["RTX PRO 4000 Blackwell \/ 2x2TB + 2x4TB"],"price":15565854,"weight":5000,"compare_at_price":18679025,"inventory_management":null,"barcode":"199764756268","requires_selling_plan":false,"selling_plan_allocations":[],"quantity_rule":{"min":1,"max":null,"increment":1}},{"id":48537000247554,"title":"No Graphics Card \/ 4x2TB SED","option1":"No Graphics Card \/ 4x2TB SED","option2":null,"option3":null,"sku":"GPUonly","requires_shipping":true,"taxable":true,"featured_image":null,"available":true,"name":"HP ZGX Fury G1n GB300 AI Workstation - No Graphics Card \/ 4x2TB SED","public_title":"No Graphics Card \/ 4x2TB SED","options":["No Graphics Card \/ 4x2TB SED"],"price":14306859,"weight":5000,"compare_at_price":17168231,"inventory_management":null,"barcode":"199764756268","requires_selling_plan":false,"selling_plan_allocations":[],"quantity_rule":{"min":1,"max":null,"increment":1}}],"images":["\/\/lioncityco.com\/cdn\/shop\/files\/hp-zgx-fury-g1n-gb300-ai-workstation-with-nvidia-blackwell-ultra-8763053.png?v=1789998912"],"featured_image":"\/\/lioncityco.com\/cdn\/shop\/files\/hp-zgx-fury-g1n-gb300-ai-workstation-with-nvidia-blackwell-ultra-8763053.png?v=1789998912","options":["Configuration"],"media":[{"alt":"HP ZGX Fury G1n GB300 AI Workstation","id":40636867019010,"position":1,"preview_image":{"aspect_ratio":0.996,"height":564,"width":562,"src":"\/\/lioncityco.com\/cdn\/shop\/files\/hp-zgx-fury-g1n-gb300-ai-workstation-with-nvidia-blackwell-ultra-8763053.png?v=1789998912"},"aspect_ratio":0.996,"height":564,"media_type":"image","src":"\/\/lioncityco.com\/cdn\/shop\/files\/hp-zgx-fury-g1n-gb300-ai-workstation-with-nvidia-blackwell-ultra-8763053.png?v=1789998912","width":562}],"requires_selling_plan":false,"selling_plan_groups":[],"content":"\u003cp style=\"margin:1em 0\"\u003eThe HP ZGX Fury G1n is an enterprise desktop AI supercomputer built around the NVIDIA Grace Blackwell Ultra (GB300) Superchip. Delivering up to 20 PFLOPS of FP4 AI compute, it accelerates training, fine-tuning, and deployment of large language models up to 1 trillion parameters, AI agents, and scientific simulations within a local infrastructure.\u003c\/p\u003e\u003cp style=\"margin:1em 0\"\u003eEquipped with 748 GB of coherent unified memory combining 252 GB HBM3e GPU memory at 7.1 TB\/s and 496 GB LPDDR5X CPU memory linked via NVLink-C2C at 900 GB\/s, this workstation enables low-latency data throughput for complex retrieval-augmented generation and digital twin workloads.\u003c\/p\u003e\u003cp style=\"margin:1em 0\"\u003ePowered by a 72-core NVIDIA Grace Arm Neoverse V2 CPU alongside dual 400 GbE QSFP NVIDIA ConnectX-8 SuperNIC networking, the ZGX Fury G1n provides high-throughput clustering capabilities and datacentre-class cooling designed for continuous 24\/7 workstation operation without specialized liquid racks.\u003c\/p\u003e\n\u003ctable class=\"pu-table\" style=\"width:100%;border-collapse:separate;border-spacing:0;border:0;box-shadow:none;outline:none;background:none;table-layout:fixed;margin:0 0 1em\"\u003e\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd style=\"border:0;padding:0.4em 0.75em 0.4em 0;opacity:0.65;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003eBrand\u003c\/td\u003e\n\u003ctd style=\"border:0;padding:0.4em 0;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003eHP\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"border:0;padding:0.4em 0.75em 0.4em 0;opacity:0.65;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003eModel\u003c\/td\u003e\n\u003ctd style=\"border:0;padding:0.4em 0;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003eHP ZGX Fury G1n\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"border:0;padding:0.4em 0.75em 0.4em 0;opacity:0.65;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003eProduct Type\u003c\/td\u003e\n\u003ctd style=\"border:0;padding:0.4em 0;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003eEnterprise Desktop AI Supercomputer \/ AI Workstation\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"border:0;padding:0.4em 0.75em 0.4em 0;opacity:0.65;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003eProcessor Platform\u003c\/td\u003e\n\u003ctd style=\"border:0;padding:0.4em 0;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003eNVIDIA GB300 Grace Blackwell Ultra Superchip\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"border:0;padding:0.4em 0.75em 0.4em 0;opacity:0.65;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003eCPU\u003c\/td\u003e\n\u003ctd style=\"border:0;padding:0.4em 0;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003e1 × NVIDIA Grace (72-Core Arm Neoverse V2)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"border:0;padding:0.4em 0.75em 0.4em 0;opacity:0.65;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003eGPU\u003c\/td\u003e\n\u003ctd style=\"border:0;padding:0.4em 0;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003e1 × NVIDIA Blackwell Ultra\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"border:0;padding:0.4em 0.75em 0.4em 0;opacity:0.65;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003eTotal Coherent Memory\u003c\/td\u003e\n\u003ctd style=\"border:0;padding:0.4em 0;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003e748 GB Unified\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"border:0;padding:0.4em 0.75em 0.4em 0;opacity:0.65;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003eGPU Memory\u003c\/td\u003e\n\u003ctd style=\"border:0;padding:0.4em 0;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003e252 GB HBM3e, 7.1 TB\/s\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"border:0;padding:0.4em 0.75em 0.4em 0;opacity:0.65;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003eCPU Memory\u003c\/td\u003e\n\u003ctd style=\"border:0;padding:0.4em 0;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003e496 GB LPDDR5X, 396 GB\/s\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"border:0;padding:0.4em 0.75em 0.4em 0;opacity:0.65;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003eInterconnect\u003c\/td\u003e\n\u003ctd style=\"border:0;padding:0.4em 0;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003eNVLink-C2C (900 GB\/s)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"border:0;padding:0.4em 0.75em 0.4em 0;opacity:0.65;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003eAI Performance\u003c\/td\u003e\n\u003ctd style=\"border:0;padding:0.4em 0;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003eUp to 20 PFLOPS FP4 Tensor Core\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"border:0;padding:0.4em 0.75em 0.4em 0;opacity:0.65;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003eModel Support\u003c\/td\u003e\n\u003ctd style=\"border:0;padding:0.4em 0;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003eUp to 1 Trillion Parameters\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"border:0;padding:0.4em 0.75em 0.4em 0;opacity:0.65;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003eGPU Partitioning\u003c\/td\u003e\n\u003ctd style=\"border:0;padding:0.4em 0;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003eMulti-Instance GPU (MIG) Up to 7 Instances\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"border:0;padding:0.4em 0.75em 0.4em 0;opacity:0.65;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003eNetworking\u003c\/td\u003e\n\u003ctd style=\"border:0;padding:0.4em 0;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003eNVIDIA ConnectX-8 (Up to 800 Gb\/s Ethernet, 2 × QSFP 400 Gb\/s)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"border:0;padding:0.4em 0.75em 0.4em 0;opacity:0.65;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003eStandard Ethernet\u003c\/td\u003e\n\u003ctd style=\"border:0;padding:0.4em 0;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003e10 GbE + 1 GbE Management\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"border:0;padding:0.4em 0.75em 0.4em 0;opacity:0.65;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003eStorage Interface\u003c\/td\u003e\n\u003ctd style=\"border:0;padding:0.4em 0;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003eM.2 Gen 5 Platform Slots\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"border:0;padding:0.4em 0.75em 0.4em 0;opacity:0.65;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003eOperating System\u003c\/td\u003e\n\u003ctd style=\"border:0;padding:0.4em 0;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003eUbuntu with NVIDIA AI Developer Tools (DGX Software Stack)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"border:0;padding:0.4em 0.75em 0.4em 0;opacity:0.65;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003ePower Supply\u003c\/td\u003e\n\u003ctd style=\"border:0;padding:0.4em 0;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003eHP Enterprise High-Efficiency Power Supply (~1,600 W Platform)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"border:0;padding:0.4em 0.75em 0.4em 0;opacity:0.65;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003eCooling\u003c\/td\u003e\n\u003ctd style=\"border:0;padding:0.4em 0;vertical-align:top;border-bottom:1px solid rgba(128,128,128,0.16);border-bottom:1px solid color-mix(in srgb,currentColor 12%,transparent)\"\u003eDatacentre-Class Component Cooling\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"border:0;padding:0.4em 0.75em 0.4em 0;opacity:0.65;vertical-align:top\"\u003eWeight\u003c\/td\u003e\n\u003ctd style=\"border:0;padding:0.4em 0;vertical-align:top\"\u003e24.5 kg\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003c\/tbody\u003e\u003c\/table\u003e"}