{"title":"NVIDIA","description":null,"products":[{"product_id":"msi-edgexpert-ms-c931-8211-ai-supercomputer-based-on-nvidia-dgx-spark-platform-for-deep-learning","title":"MSI EdgeXpert MS-C931 – AI Supercomputer Based on NVIDIA DGX Spark Platform for Deep Learning","description":"\u003cp\u003eThe MSI EdgeXpert MS-C931 is a desktop-class AI supercomputer built on the NVIDIA DGX Spark platform. It suits developers, researchers and data scientists who want data-center-grade AI capability on their own desk instead of metered by the hour in the cloud. It pairs the NVIDIA GB10 Grace Blackwell Superchip with 128GB of unified memory in a 1.19-litre chassis, and MSI adds a curated software ecosystem.\u003c\/p\u003e\u003ch2\u003eWho it's for\u003c\/h2\u003e\u003cul\u003e\n\u003cli\u003eDevelopers and researchers fine-tuning, quantizing and serving models up to roughly 200B parameters\u003c\/li\u003e\n\u003cli\u003eTeams building legal AI, machine vision, offline voice translation or agentic AI products with the bundled software\u003c\/li\u003e\n\u003cli\u003eTeams with data-residency or IP concerns keeping datasets and model weights on-premises\u003c\/li\u003e\n\u003c\/ul\u003e\u003ch2\u003eKey features\u003c\/h2\u003e\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003eNVIDIA GB10 Grace Blackwell Superchip:\u003c\/strong\u003e a 20-core Arm CPU (10x Cortex-X925 + 10x Cortex-A725) fused to a Blackwell-architecture GPU over NVIDIA NVLink-C2C, delivering 1000 AI TOPS \/ 1 petaFLOP of FP4 (sparse) performance.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003e128GB unified LPDDR5x memory at 273GB\/s:\u003c\/strong\u003e a single coherent 256-bit memory pool shared between CPU and GPU, holding models up to roughly 200B parameters (and up to 405B across two stacked units via ConnectX-7).\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003e1TB or 4TB self-encrypting NVMe SSD:\u003c\/strong\u003e hardware self-encryption at either tier.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eNVIDIA ConnectX-7 Smart NIC (200Gbps):\u003c\/strong\u003e data-center-class networking for clustering two units, plus 10GbE, Wi-Fi 7 and Bluetooth 5.4.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eNVIDIA DGX OS pre-installed:\u003c\/strong\u003e the full NVIDIA AI stack ships ready to run, and work is container-portable to other DGX Spark-class systems or DGX Cloud.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eCurated third-party AI software:\u003c\/strong\u003e MSI ships access to AIPLUX Legal AI Suite, Memorence Operagents (machine vision and operational AI), Ubestream offline voice translation and Galene.AI Elettra’s agentic AI platform.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eCompact and quiet:\u003c\/strong\u003e a 151 x 151 x 52mm, 1.2kg chassis with smart fan control, 4x USB 3.2 Type-C, HDMI 2.1a and 3x DisplayPort 1.4a.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eEnterprise reliability:\u003c\/strong\u003e TPM onboard, a 0–35°C operating temperature range, and FCC\/CE\/UKCA\/VCCI\/BSMI certification.\u003c\/li\u003e\n\u003c\/ul\u003e\u003ch2\u003eSpecifications\u003c\/h2\u003e\u003ctable\u003e\n\u003cthead\u003e\u003ctr\u003e\n\u003cth\u003eSpec\u003c\/th\u003e\n\u003cth\u003eDetail\u003c\/th\u003e\n\u003c\/tr\u003e\u003c\/thead\u003e\n\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd\u003eModel Number\u003c\/td\u003e\n\u003ctd\u003eEdgeXpert MS-C931\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eArchitecture\u003c\/td\u003e\n\u003ctd\u003eNVIDIA Grace Blackwell GB10 Superchip\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eCPU\u003c\/td\u003e\n\u003ctd\u003e20-core Arm (10x Cortex-X925 + 10x Cortex-A725)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eCPU-GPU Interconnect\u003c\/td\u003e\n\u003ctd\u003eNVIDIA NVLink-C2C\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eTensor Performance\u003c\/td\u003e\n\u003ctd\u003e1 petaFLOP (1000 AI TOPS), FP4, Sparse\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eSystem Memory\u003c\/td\u003e\n\u003ctd\u003e128GB LPDDR5x coherent unified system memory\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eMemory Interface \/ Bandwidth\u003c\/td\u003e\n\u003ctd\u003e256-bit \/ 273GB\/s\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eStorage\u003c\/td\u003e\n\u003ctd\u003e1TB or 4TB NVMe M.2 SSD with self-encryption\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eUSB\u003c\/td\u003e\n\u003ctd\u003e4x USB 3.2 Type-C\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eEthernet\u003c\/td\u003e\n\u003ctd\u003e1x RJ-45 (10GbE)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eNetwork Interface Card\u003c\/td\u003e\n\u003ctd\u003eNVIDIA ConnectX-7 Smart NIC (200Gbps)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eDisplay Connectors\u003c\/td\u003e\n\u003ctd\u003e1x HDMI 2.1a; 3x DisplayPort 1.4a via USB-C\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eVideo Encode\/Decode\u003c\/td\u003e\n\u003ctd\u003e1x NVENC \/ 1x NVDEC\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eTPM \/ Smart Fan Control\u003c\/td\u003e\n\u003ctd\u003eYes \/ Yes\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eOperating System\u003c\/td\u003e\n\u003ctd\u003eNVIDIA DGX OS\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eMax Model Size\u003c\/td\u003e\n\u003ctd\u003eUp to 200B parameters (405B via dual-unit ConnectX stacking)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eDimensions\u003c\/td\u003e\n\u003ctd\u003e151 x 151 x 52mm (1.19L)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eWeight\u003c\/td\u003e\n\u003ctd\u003e1.2kg\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eOperating Temperature \/ Humidity\u003c\/td\u003e\n\u003ctd\u003e0–35°C \/ 10–90% non-condensing\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eStorage Temperature \/ Humidity\u003c\/td\u003e\n\u003ctd\u003e0–60°C \/ 10–90% non-condensing\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003ePower Supply\u003c\/td\u003e\n\u003ctd\u003e~240W via USB-C with external adapter\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eCertifications\u003c\/td\u003e\n\u003ctd\u003eFCC Class B, CE, UKCA, VCCI, BSMI\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eBundled AI Software\u003c\/td\u003e\n\u003ctd\u003eAIPLUX Legal AI Suite, Memorence Operagents, Ubestream Voice Translation, Galene.AI Elettra\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eIn the Box\u003c\/td\u003e\n\u003ctd\u003eEdgeXpert MS-C931 system, external ~240W USB-C power adapter, power cord, quick start guide\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003c\/tbody\u003e\n\u003c\/table\u003e\u003ch2\u003eGood to know\u003c\/h2\u003e\u003cul\u003e\n\u003cli\u003eThe 1 petaFLOP \/ 1000 TOPS figure is a peak FP4-sparse number. Real dense-precision throughput on a given model will be lower.\u003c\/li\u003e\n\u003cli\u003eTraining a foundation model from scratch is still cluster or cloud territory. This machine is built for fine-tuning, quantization, inference serving and applied-AI development.\u003c\/li\u003e\n\u003cli\u003eA 70B model in FP4\/INT4 quantization, or a 30B model at higher precision with a long context window, runs without memory workarounds.\u003c\/li\u003e\n\u003cli\u003eChoose 1TB for a handful of active checkpoints and datasets, or 4TB for multiple quantized variants, larger training corpora or a growing library of fine-tuned checkpoints.\u003c\/li\u003e\n\u003c\/ul\u003e\u003cp\u003ePick the MS-C931 over a bare DGX Spark unit if the bundled software overlaps with what you are building.\u003c\/p\u003e","brand":"NVIDIA","offers":[{"title":"4 TB","offer_id":58232536269182,"sku":"MSI-EDGEXPERT-MSC932","price":6499.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1022\/4468\/0062\/files\/product_175686100704b1a75fc1f20b2de1b0354880526c9a_f33d2699-cf99-4e2c-97ab-a8f795e8b410.webp?v=1792094004"},{"product_id":"nvidia-rtx-pro-6000-blackwell-server-edition-96gb","title":"NVIDIA RTX PRO 6000 Blackwell Server Edition (96GB)","description":"\u003cp\u003eThe NVIDIA RTX PRO 6000 Blackwell Server Edition is a 96GB GDDR7 ECC graphics card for server deployments running generative AI, scientific computing, rendering and video workloads. It combines large ECC-protected graphics memory with dedicated AI and ray-tracing hardware. It suits teams that already have a compatible server chassis and need a lot of GPU memory in a single card.\u003c\/p\u003e\u003ch2\u003eWho it's for\u003c\/h2\u003e\u003cul\u003e\n\u003cli\u003eRunning large models, datasets and complex scenes that need 96GB of GPU memory\u003c\/li\u003e\n\u003cli\u003eFP4 inference on fifth-generation Tensor cores\u003c\/li\u003e\n\u003cli\u003eSharing one GPU between up to four isolated workloads with MIG\u003c\/li\u003e\n\u003cli\u003eDemanding video pipelines that use four encode and four decode engines\u003c\/li\u003e\n\u003c\/ul\u003e\u003ch2\u003eKey features\u003c\/h2\u003e\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003e96GB GDDR7 ECC:\u003c\/strong\u003e Capacity for large models, datasets and complex scenes, with 1,597 GB\/s memory bandwidth.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eBlackwell acceleration:\u003c\/strong\u003e Fifth-generation Tensor cores support FP4 inference, while fourth-generation RT cores accelerate ray tracing.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eShared GPU resources:\u003c\/strong\u003e MIG partitions one GPU into up to four isolated instances with dedicated resources.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eProfessional media processing:\u003c\/strong\u003e Four encode and four decode engines support demanding video pipelines.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eBuilt-in security:\u003c\/strong\u003e Confidential computing and secure boot with root of trust.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003ePassive cooling:\u003c\/strong\u003e The heatsink relies on airflow provided by the server.\u003c\/li\u003e\n\u003c\/ul\u003e\u003ch2\u003eSpecifications\u003c\/h2\u003e\u003ctable\u003e\n\u003cthead\u003e\u003ctr\u003e\n\u003cth\u003eSpec\u003c\/th\u003e\n\u003cth\u003eDetail\u003c\/th\u003e\n\u003c\/tr\u003e\u003c\/thead\u003e\n\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd\u003eArchitecture\u003c\/td\u003e\n\u003ctd\u003eNVIDIA Blackwell\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eGPU memory\u003c\/td\u003e\n\u003ctd\u003e96 GB GDDR7 with ECC\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eMemory interface\u003c\/td\u003e\n\u003ctd\u003e512-bit\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eMemory bandwidth\u003c\/td\u003e\n\u003ctd\u003e1,597 GB\/s\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eCUDA cores\u003c\/td\u003e\n\u003ctd\u003e24,064\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eTensor cores\u003c\/td\u003e\n\u003ctd\u003e752, fifth generation\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eRT cores\u003c\/td\u003e\n\u003ctd\u003e188, fourth generation\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eFP32 performance\u003c\/td\u003e\n\u003ctd\u003e120 TFLOPS\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003ePeak FP4 Tensor performance\u003c\/td\u003e\n\u003ctd\u003e4 PFLOPS\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003ePeak FP8 Tensor performance\u003c\/td\u003e\n\u003ctd\u003e2 PFLOPS\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003ePeak FP16 \/ BF16 Tensor performance\u003c\/td\u003e\n\u003ctd\u003e1 PFLOP\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003ePeak TF32 Tensor performance\u003c\/td\u003e\n\u003ctd\u003e234 TFLOPS\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003ePeak RT core performance\u003c\/td\u003e\n\u003ctd\u003e355 TFLOPS\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eHost interface\u003c\/td\u003e\n\u003ctd\u003ePCI Express 5.0 x16\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eMulti-Instance GPU\u003c\/td\u003e\n\u003ctd\u003eUp to 4 isolated instances; up to 24 GB per instance\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eVideo engines\u003c\/td\u003e\n\u003ctd\u003e4 ninth-generation NVENC; 4 sixth-generation NVDEC\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eCooling\u003c\/td\u003e\n\u003ctd\u003ePassive heatsink; requires server-provided airflow\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eMaximum board power\u003c\/td\u003e\n\u003ctd\u003eUp to 600 W, configurable\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003ePower connector\u003c\/td\u003e\n\u003ctd\u003e1 × PCIe CEM5 16-pin\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eForm factor\u003c\/td\u003e\n\u003ctd\u003eFull-height, full-length, dual-slot\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eCard dimensions\u003c\/td\u003e\n\u003ctd\u003e4.4 inches high × 10.5 inches long\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eDisplay connectors\u003c\/td\u003e\n\u003ctd\u003e4 × DisplayPort 2.1\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eNVLink\u003c\/td\u003e\n\u003ctd\u003eNot supported\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eSecurity\u003c\/td\u003e\n\u003ctd\u003eConfidential computing; secure boot with root of trust\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003c\/tbody\u003e\n\u003c\/table\u003e\u003ch2\u003eGood to know\u003c\/h2\u003e\u003cul\u003e\n\u003cli\u003ePerformance figures are manufacturer-rated peaks; application throughput depends on precision, software and system configuration.\u003c\/li\u003e\n\u003cli\u003eThis listing is for the passive, air-cooled Server Edition GPU card. Its heatsink depends on forced airflow from a compatible server chassis.\u003c\/li\u003e\n\u003cli\u003eConfirm chassis clearance, PCIe slot support, power cabling and cooling capacity before installation.\u003c\/li\u003e\n\u003cli\u003eIt is not a complete server.\u003c\/li\u003e\n\u003cli\u003eOptional enterprise software licensing is separate unless expressly included in your order.\u003c\/li\u003e\n\u003cli\u003eManufacturer documentation referenced by the original listing: NVIDIA product specifications, PNY specifications, and a product brief with integration requirements.\u003c\/li\u003e\n\u003c\/ul\u003e\u003cp\u003eChoose this card if your server can feed a passive, dual-slot card with forced airflow and you want 96GB of ECC memory per GPU. If you need a complete machine rather than a component, look at the full systems in the ComputaHardware range instead.\u003c\/p\u003e","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":58232536301950,"sku":"RTX-pro-6000-blackwell-server-edition-96gb","price":15339.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1022\/4468\/0062\/files\/nvidia-rtx-pro-6000-blackwell-server-edition_17d67567-32ee-4b89-b48b-60403da72568.png?v=1792094006"},{"product_id":"nvidia-dgx-spark-8211-personal-ai-desktop-supercomputer-desktop-gb10-grace-blackwell-chip","title":"NVIDIA DGX Spark™ – Personal AI Desktop Supercomputer – Desktop GB10 Grace Blackwell Chip","description":"\u003cp\u003eThe NVIDIA DGX Spark puts data-center-class AI compute in a chassis the size of a hardback book. It is built for machine learning engineers, researchers and small AI teams who need to prototype, fine-tune and run large models locally instead of queuing for cluster time or paying cloud GPU bills. If you spin up an A100 or H100 instance every time you test a fine-tune, this replaces that loop with hardware on your desk, with no idle-GPU billing and no dataset leaving the building.\u003c\/p\u003e\u003ch2\u003eWho it's for\u003c\/h2\u003e\u003cul\u003e\n\u003cli\u003eFine-tuning an open-weight 70B model with LoRA\/QLoRA\u003c\/li\u003e\n\u003cli\u003eIterating on a RAG pipeline against a private document set, offline and air-gapped if required\u003c\/li\u003e\n\u003cli\u003eBenchmarking quantization and serving inference for models in the 70B–200B class\u003c\/li\u003e\n\u003c\/ul\u003e\u003ch2\u003eKey features\u003c\/h2\u003e\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003eNVIDIA GB10 Grace Blackwell Superchip:\u003c\/strong\u003e a 20-core Arm CPU (10x Cortex-X925 performance cores + 10x Cortex-A725 efficiency cores) fused to a Blackwell-architecture GPU with 5th-generation Tensor Cores and 4th-generation RT Cores over NVLink-C2C, rated for up to 1 petaFLOP of FP4 AI compute with sparsity.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003e128GB unified LPDDR5x memory at 273GB\/s:\u003c\/strong\u003e CPU and GPU share one coherent 128GB pool over a 256-bit memory interface, with no PCIe round-trip copying between system RAM and VRAM. It holds models that would run out of memory on a 24GB or even 48GB discrete workstation GPU.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eRun and fine-tune models up to ~200B parameters:\u003c\/strong\u003e at FP4 precision, a single unit hosts models in the 70B–200B class for local inference, LoRA\/QLoRA fine-tuning and RAG pipeline development.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003e4TB self-encrypting NVMe SSD:\u003c\/strong\u003e local headroom for multiple model checkpoints, quantized variants, container images and full training datasets.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eConnectX-7 Smart NIC (200Gbps):\u003c\/strong\u003e pair two DGX Spark units with a certified QSFP112 interconnect cable to pool 256GB of unified memory and run inference on models up to roughly 405B parameters.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eFull NVIDIA DGX OS + AI stack, pre-installed:\u003c\/strong\u003e CUDA, cuDNN, NCCL, PyTorch and TensorFlow containers, NVIDIA AI Workbench, and accelerated frameworks such as Isaac, Metropolis and Holoscan. Workloads are container-portable to other Blackwell systems or DGX Cloud without code changes.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eDesktop footprint:\u003c\/strong\u003e 150 x 150 x 50.5mm and 1.2kg, powered from a single 240W supply, with 1x HDMI 2.1a and up to 3x DisplayPort 2.1 over USB-C.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eConnectivity:\u003c\/strong\u003e 4x USB Type-C, 10 Gigabit Ethernet, Wi-Fi 7, Bluetooth 5.4.\u003c\/li\u003e\n\u003c\/ul\u003e\u003ch2\u003eSpecifications\u003c\/h2\u003e\u003ctable\u003e\n\u003cthead\u003e\u003ctr\u003e\n\u003cth\u003eSpec\u003c\/th\u003e\n\u003cth\u003eDetail\u003c\/th\u003e\n\u003c\/tr\u003e\u003c\/thead\u003e\n\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd\u003eSuperchip\u003c\/td\u003e\n\u003ctd\u003eNVIDIA GB10 Grace Blackwell\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eCPU\u003c\/td\u003e\n\u003ctd\u003e20-core Arm (10x Cortex-X925 + 10x Cortex-A725)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eGPU\u003c\/td\u003e\n\u003ctd\u003eNVIDIA Blackwell architecture, 5th Gen Tensor Cores, 4th Gen RT Cores\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eCPU-GPU Interconnect\u003c\/td\u003e\n\u003ctd\u003eNVLink-C2C\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eAI Performance\u003c\/td\u003e\n\u003ctd\u003eUp to 1 petaFLOP (FP4, with sparsity)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eSystem Memory\u003c\/td\u003e\n\u003ctd\u003e128GB LPDDR5x, coherent unified memory\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eMemory Interface \/ Bandwidth\u003c\/td\u003e\n\u003ctd\u003e256-bit \/ up to 273GB\/s\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eStorage\u003c\/td\u003e\n\u003ctd\u003e4TB NVMe M.2, self-encrypting\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eNetworking\u003c\/td\u003e\n\u003ctd\u003eNVIDIA ConnectX-7 Smart NIC (200Gbps), 10 Gigabit Ethernet (RJ-45), Wi-Fi 7, Bluetooth 5.4\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eUSB\u003c\/td\u003e\n\u003ctd\u003e4x USB Type-C\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eDisplay Outputs\u003c\/td\u003e\n\u003ctd\u003e1x HDMI 2.1a, up to 3x DisplayPort 2.1 (USB-C DP Alt Mode)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eVideo Encode\/Decode\u003c\/td\u003e\n\u003ctd\u003e1x NVENC \/ 1x NVDEC\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eOperating System\u003c\/td\u003e\n\u003ctd\u003eNVIDIA DGX OS with full NVIDIA AI software stack (CUDA, cuDNN, NCCL, container runtime)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eMax Model Size\u003c\/td\u003e\n\u003ctd\u003e~200B parameters (single unit); ~405B parameters (dual-unit clustered, 256GB pooled memory)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003ePower Supply\u003c\/td\u003e\n\u003ctd\u003e240W (GB10 TDP 140W)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eDimensions\u003c\/td\u003e\n\u003ctd\u003e150 x 150 x 50.5mm\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eWeight\u003c\/td\u003e\n\u003ctd\u003e1.2kg\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eConfigurations\u003c\/td\u003e\n\u003ctd\u003eSingle Unit; Dual Unit + Interconnect Cable (NVIDIA-certified ConnectX-7 QSFP112)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003c\/tbody\u003e\n\u003c\/table\u003e\u003ch2\u003eGood to know\u003c\/h2\u003e\u003cul\u003e\n\u003cli\u003eThe 1 petaFLOP figure is a peak FP4-with-sparsity number. Real dense-precision throughput will be lower.\u003c\/li\u003e\n\u003cli\u003eIt is not a from-scratch training rig: with 273GB\/s memory bandwidth and single-GPU-equivalent compute, pre-training multi-billion-parameter models from random initialization is cluster or cloud territory.\u003c\/li\u003e\n\u003cli\u003eA 70B model in FP4\/INT4 quantization, or a 30B model at higher precision with generous context length, loads without tensor-parallel sharding.\u003c\/li\u003e\n\u003cli\u003eTwo configurations: a Single Unit, or a Dual Unit + Interconnect Cable bundle (two units plus an NVIDIA-certified ConnectX-7 QSFP112 cable) for 256GB of pooled memory.\u003c\/li\u003e\n\u003c\/ul\u003e\u003cp\u003eChoose the single unit if your largest model fits in 128GB, or the dual-unit bundle for models up to roughly 405B parameters.\u003c\/p\u003e","brand":"NVIDIA","offers":[{"title":"Single Unit","offer_id":58232537219454,"sku":"NVIDIA-DGXSPARK-SINGLE","price":4699.0,"currency_code":"USD","in_stock":true},{"title":"Dual Unit + Interconnect Cable","offer_id":58232537252222,"sku":"NVIDIA-DGXSPARK-DUAL","price":9617.99,"currency_code":"USD","in_stock":false}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1022\/4468\/0062\/files\/516QauLL31L._SL1500_faf69533-16fc-49ac-8eb7-e3869a4085db.jpg?v=1792094024"},{"product_id":"avermedia-d133onb-industrial-box-pc-nvidia-jetson-orin-nx-orin-nano","title":"AVerMedia D133ONB Industrial Box PC — NVIDIA Jetson Orin NX\/Orin Nano","description":"\u003cp\u003eThe AVerMedia D133ONB is an ultra-compact industrial box PC built around NVIDIA Jetson Orin Nano and Orin NX modules. It is designed for engineers who need to take a computer-vision or edge AI application from prototype to field deployment in a footprint where a full-size industrial PC will not fit. If your project needs dual-camera capture and real-time inferencing in a space smaller than a lunchbox, this is built for it.\u003c\/p\u003e\u003ch2\u003eWho it's for\u003c\/h2\u003e\u003cul\u003e\n\u003cli\u003eStereo vision and dual-angle camera projects that need two native camera inputs without an external capture card\u003c\/li\u003e\n\u003cli\u003eSmart retail, smart camera and smart city deployments, where an open dev-kit board is a liability\u003c\/li\u003e\n\u003cli\u003eMachine-vision, AIoT and robotics teams moving from a Jetson developer kit to field-hardened hardware\u003c\/li\u003e\n\u003cli\u003eCabinets, kiosks and outdoor enclosures that see real temperature swings\u003c\/li\u003e\n\u003c\/ul\u003e\u003ch2\u003eKey features\u003c\/h2\u003e\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003eNVIDIA Jetson Orin Nano or Orin NX module:\u003c\/strong\u003e the D133ONB ships with an Orin Nano 8GB module, while the closely related D133OXB variant offers Orin NX 8GB or 16GB for higher throughput. Both are ready for computer-vision and edge AI inferencing, with no separate carrier-board integration required.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003ePocket-sized chassis:\u003c\/strong\u003e 93 x 81.2 x 81.9mm, for deployments where every centimeter of cabinet or enclosure space is already spoken for.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eDual MIPI camera inputs:\u003c\/strong\u003e 2x 4-lane MIPI CSI-2 connectors (22-pin FPC, 0.5mm pitch) for stereo vision, dual-angle coverage or independent camera feeds without an external capture card.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003e256GB NVMe SSD included:\u003c\/strong\u003e a pre-installed M.2 Key M 2280 NVMe drive ships standard, so there is no separate storage purchase before you can start deploying.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eDisplay and networking built in:\u003c\/strong\u003e HDMI output at up to 4K30 (Orin Nano) or 4K60 (Orin NX), 1x Gigabit Ethernet (RJ-45) and an M.2 Key E slot for Wi-Fi.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eIndustrial expansion header:\u003c\/strong\u003e a 20-pin header exposing 2x I2C, 1x UART and 9x GPIO for sensor integration, actuator control and custom hardware triggers.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eWide operating range:\u003c\/strong\u003e rated from –25°C to 60°C for cabinets, kiosks and outdoor enclosures.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eRTC battery and health monitoring:\u003c\/strong\u003e an onboard real-time clock with MCU-monitored battery life, useful for unattended installations.\u003c\/li\u003e\n\u003c\/ul\u003e\u003ch2\u003eSpecifications\u003c\/h2\u003e\u003ctable\u003e\n\u003cthead\u003e\u003ctr\u003e\n\u003cth\u003eSpec\u003c\/th\u003e\n\u003cth\u003eDetail\u003c\/th\u003e\n\u003c\/tr\u003e\u003c\/thead\u003e\n\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd\u003eCompute Module\u003c\/td\u003e\n\u003ctd\u003eNVIDIA Jetson Orin Nano 8GB (D133ONB) \/ Orin NX 8GB or 16GB (D133OXB variant)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eStorage\u003c\/td\u003e\n\u003ctd\u003eM.2 Key M 2280 NVMe, 256GB SSD pre-installed\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eDisplay Output\u003c\/td\u003e\n\u003ctd\u003e1x HDMI, up to 4K30 (Orin Nano) \/ 4K60 (Orin NX)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eCamera Inputs\u003c\/td\u003e\n\u003ctd\u003e2x 4-lane MIPI CSI-2 (22-pin FPC, 0.5mm pitch)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eUSB\u003c\/td\u003e\n\u003ctd\u003e2x USB 3.2 Type-A, 1x USB 2.0 Type-C (recovery)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eNetworking\u003c\/td\u003e\n\u003ctd\u003e1x Gigabit Ethernet (RJ-45), M.2 Key E 2230 for Wi-Fi\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eExpansion Header\u003c\/td\u003e\n\u003ctd\u003e20-pin, 2x I2C, 1x UART, 9x GPIO\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003ePower Input\u003c\/td\u003e\n\u003ctd\u003e12V\/5A via 3.5mm screw terminal, 9–24V accepted range\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003ePower Consumption\u003c\/td\u003e\n\u003ctd\u003eApprox. 14.4–31.5W depending on module and load\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eOperating Temperature\u003c\/td\u003e\n\u003ctd\u003e–25°C to 60°C\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eStorage Temperature\u003c\/td\u003e\n\u003ctd\u003e–40°C to 85°C\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eDimensions\u003c\/td\u003e\n\u003ctd\u003e93 x 81.2 x 81.9mm\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eWeight\u003c\/td\u003e\n\u003ctd\u003eApprox. 500g\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eRTC\u003c\/td\u003e\n\u003ctd\u003eOnboard real-time clock with MCU battery-life monitoring\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eOperating System\u003c\/td\u003e\n\u003ctd\u003eNVIDIA JetPack \/ L4T (Ubuntu-based)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eCertifications\u003c\/td\u003e\n\u003ctd\u003eCE, FCC, KC\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eTarget Applications\u003c\/td\u003e\n\u003ctd\u003eSmart retail, smart camera systems, smart city, AIoT, machine vision, robotics\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003c\/tbody\u003e\n\u003c\/table\u003e\u003ch2\u003eGood to know\u003c\/h2\u003e\u003cul\u003e\n\u003cli\u003eAVerMedia does not publish a specific AI TOPS figure for the D133ONB. The number that matters is the Jetson module’s own published rating: NVIDIA’s Orin Nano and Orin NX modules span roughly 40–100 TOPS depending on configuration and Super Mode, and the module you select sets that ceiling.\u003c\/li\u003e\n\u003cli\u003eThis is an inferencing and computer-vision deployment platform running the standard NVIDIA JetPack\/L4T stack, so models trained and validated on a Jetson developer kit deploy with minimal changes.\u003c\/li\u003e\n\u003cli\u003eAVerMedia positions the D133\/DX33 box PC family for smart retail, smart camera and smart city solutions.\u003c\/li\u003e\n\u003c\/ul\u003e\u003cp\u003ePick the D133ONB when you need a sealed, mount-and-forget Jetson box with two native camera inputs. If you need an Orin NX module for higher throughput, look at the D133OXB variant instead.\u003c\/p\u003e","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":58232537416062,"sku":"D133ONB","price":1156.78,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1022\/4468\/0062\/files\/avermedia-d133onb-3_c6c6b417-d6bf-4304-96e1-df943adeb8b7.jpg?v=1792094028"},{"product_id":"acer-veriton-vgn100-ud11-dgx-spark-ai-workstation-nvidia-gb10-grace-blackwell","title":"Acer Veriton VGN100-UD11 — DGX Spark AI Workstation (NVIDIA GB10 Grace Blackwell)","description":"\u003cp\u003eThe Acer Veriton VGN100-UD11 (marketed in North America as the Veriton GN100) is Acer’s entry into the NVIDIA GB10 Grace Blackwell “personal AI supercomputer” category, the same platform underpinning NVIDIA’s own DGX Spark. It packs that platform into a workstation weighing under three pounds, with Acer’s own management software on top. It suits ML engineers and small AI teams who want DGX Spark-class local compute with Acer’s build quality, monitoring tools and support channel behind it.\u003c\/p\u003e\u003ch2\u003eWho it's for\u003c\/h2\u003e\u003cul\u003e\n\u003cli\u003eML engineers running and quantizing models in the 70B–200B parameter class on their own desk\u003c\/li\u003e\n\u003cli\u003eSmall AI teams that want live visibility into GPU temperature, memory pressure and inference throughput\u003c\/li\u003e\n\u003cli\u003eDevelopers who want to move work to a DGX Spark, a DGX cluster or DGX Cloud without modification\u003c\/li\u003e\n\u003c\/ul\u003e\u003ch2\u003eKey features\u003c\/h2\u003e\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003eNVIDIA GB10 Grace Blackwell Superchip:\u003c\/strong\u003e a 20-core Arm CPU (10x Cortex-X925 performance cores + 10x Cortex-A725 efficiency cores) fused to an integrated Blackwell GB20B GPU with 5th Gen Tensor Cores and 4th Gen RT Cores, rated for up to 1 petaFLOP of FP4 AI performance.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003e128GB unified LPDDR5x memory at 273GB\/s:\u003c\/strong\u003e coherent memory shared between CPU and GPU (8533MT\/s effective), so large models load and run without the VRAM ceiling of discrete-GPU workstations.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eUp to 4TB self-encrypting NVMe SSD:\u003c\/strong\u003e the top configuration ships with a 4TB Gen5-class NVMe drive; a lower-storage SKU is also available.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eConnectX-7 Smart NIC + 10GbE:\u003c\/strong\u003e dual 200Gb\/s QSFP ports for clustering multiple units to pool memory, plus a dedicated 10 Gigabit Ethernet RJ-45 port for everyday networking.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eAcer Sense Pro management software:\u003c\/strong\u003e a dashboard layered on top of NVIDIA DGX OS with real-time CPU, GPU, memory and thermal monitoring, hardware tuning, inference benchmarking (tokens-per-second and time-to-first-token charts) and self-diagnostics.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eFull NVIDIA DGX OS + AI stack:\u003c\/strong\u003e ships on Ubuntu 24.04 LTS for Arm with NVIDIA DGX OS, PyTorch, Jupyter and Ollama pre-installed, plus NVIDIA Sync support for remote management over the network.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003ePortable footprint:\u003c\/strong\u003e 5.9 x 5.9 x 2 inches and roughly 1.2kg (2.65 lbs), powered from a 240W external adapter, with 4x USB-C ports (3x USB-C 3.2 Gen2x2 at 20Gbps carrying DisplayPort 2.1, plus 1x USB-C PD-in) and HDMI 2.1 for multi-monitor visualization.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eWireless and physical security:\u003c\/strong\u003e Wi-Fi 7, Bluetooth 5.4 and a Kensington lock slot for units deployed outside a locked server room.\u003c\/li\u003e\n\u003c\/ul\u003e\u003ch2\u003eSpecifications\u003c\/h2\u003e\u003ctable\u003e\n\u003cthead\u003e\u003ctr\u003e\n\u003cth\u003eSpec\u003c\/th\u003e\n\u003cth\u003eDetail\u003c\/th\u003e\n\u003c\/tr\u003e\u003c\/thead\u003e\n\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd\u003eModel\u003c\/td\u003e\n\u003ctd\u003eVeriton VGN100-UD11 (Veriton GN100 AI Mini Workstation)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eSuperchip\u003c\/td\u003e\n\u003ctd\u003eNVIDIA GB10 Grace Blackwell\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eCPU\u003c\/td\u003e\n\u003ctd\u003e20-core Arm (10x Cortex-X925 + 10x Cortex-A725)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eGPU\u003c\/td\u003e\n\u003ctd\u003eNVIDIA Blackwell GB20B, 5th Gen Tensor Cores, 4th Gen RT Cores\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eAI Performance\u003c\/td\u003e\n\u003ctd\u003eUp to 1 petaFLOP (FP4, with sparsity)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eMemory\u003c\/td\u003e\n\u003ctd\u003e128GB LPDDR5x unified memory, 8533MT\/s, 273GB\/s bandwidth\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eStorage\u003c\/td\u003e\n\u003ctd\u003eUp to 4TB self-encrypting NVMe SSD (lower-capacity SKUs available)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eNetworking\u003c\/td\u003e\n\u003ctd\u003eNVIDIA ConnectX-7 Smart NIC (dual 200Gb\/s QSFP), 10 Gigabit Ethernet (RJ-45)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eWireless\u003c\/td\u003e\n\u003ctd\u003eWi-Fi 7, Bluetooth 5.4\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003ePorts\u003c\/td\u003e\n\u003ctd\u003e3x USB-C 3.2 Gen2x2 (20Gbps) with DisplayPort 2.1, 1x USB-C PD-in, HDMI 2.1\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eSecurity\u003c\/td\u003e\n\u003ctd\u003eSelf-encrypting SSD, Kensington lock slot\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eSoftware\u003c\/td\u003e\n\u003ctd\u003eNVIDIA DGX OS (Ubuntu 24.04 LTS Arm), Acer Sense Pro dashboard, NVIDIA Sync, PyTorch, Jupyter, Ollama pre-installed\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003ePower Supply\u003c\/td\u003e\n\u003ctd\u003e240W external adapter\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eDimensions\u003c\/td\u003e\n\u003ctd\u003e5.9 x 5.9 x 2 inches (150 x 150 x 50.5mm)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eWeight\u003c\/td\u003e\n\u003ctd\u003eApprox. 1.2kg (2.65 lbs)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eClustering\u003c\/td\u003e\n\u003ctd\u003eMulti-unit clustering via ConnectX-7 for pooled memory on larger model classes\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003c\/tbody\u003e\n\u003c\/table\u003e\u003ch2\u003eGood to know\u003c\/h2\u003e\u003cul\u003e\n\u003cli\u003eThe 1 petaFLOP figure is a peak FP4-with-sparsity number. Real dense-precision throughput on a given model will be lower.\u003c\/li\u003e\n\u003cli\u003eThis is a fine-tuning, quantization and inference machine, not a from-scratch foundation-model trainer. That workload still belongs on a cluster.\u003c\/li\u003e\n\u003cli\u003eAcer’s original launch materials cited two linked units for models up to roughly 405B parameters. Later materials reference larger multi-unit clusters for bigger model classes.\u003c\/li\u003e\n\u003cli\u003eIt runs the identical NVIDIA DGX OS and CUDA stack as other GB10-class devices.\u003c\/li\u003e\n\u003c\/ul\u003e\u003cp\u003eThe silicon, memory design and DGX OS stack are the same across every GB10 system, so choose this one for Acer’s management tooling and its established enterprise support and warranty structure rather than for raw performance.\u003c\/p\u003e","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":58232537448830,"sku":"DT.R6LAA.001","price":6499.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1022\/4468\/0062\/files\/acer-veriton-vgn100-6_9b5d9941-fe4a-4c51-8351-0833dd8b3d66.jpg?v=1792094030"},{"product_id":"nvidia-rtx-pro-6000-blackwell-workstation-edition-96gb","title":"NVIDIA RTX PRO 6000 Blackwell Workstation Edition (96GB)","description":"\u003cp\u003eThe NVIDIA RTX PRO 6000 Blackwell Workstation Edition is NVIDIA’s flagship professional GPU. It pairs the full Blackwell GB202 die with 96GB of ECC-protected GDDR7, enough memory to hold entire large language models, massive point clouds or feature-film-resolution scenes without offloading to system RAM. It suits studios, labs and engineering teams that need workstation-class reliability and datacenter-class capacity in a single desktop tower.\u003c\/p\u003e\u003ch2\u003eWho it's for\u003c\/h2\u003e\u003cul\u003e\n\u003cli\u003eRunning 70B-parameter LLMs locally in reduced precision on a single card\u003c\/li\u003e\n\u003cli\u003eFine-tuning mid-size models without gradient checkpointing workarounds, or keeping several diffusion and vision models resident for production pipelines\u003c\/li\u003e\n\u003cli\u003eRendering film-resolution scenes in V-Ray, Arnold, Octane, Redshift and OptiX-based renderers with geometry, textures and simulation caches held in GPU memory\u003c\/li\u003e\n\u003cli\u003eCFD, FEA and digital-twin simulation, where dataset size rather than raw FLOPS is usually the limit\u003c\/li\u003e\n\u003c\/ul\u003e\u003ch2\u003eKey features\u003c\/h2\u003e\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003eFull Blackwell GB202 die:\u003c\/strong\u003e 24,064 CUDA cores across 188 streaming multiprocessors, the largest professional Blackwell configuration NVIDIA ships, built on TSMC’s 4NP process.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003e96GB GDDR7 with ECC:\u003c\/strong\u003e the largest memory pool of any NVIDIA workstation GPU, on a 512-bit bus, with error-correcting protection for mission-critical simulation and inference work.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003e1,792GB\/s memory bandwidth:\u003c\/strong\u003e feeds the compute cores for real-time AI inference, fluid and structural simulation, and multi-layer 8K compositing.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003e752 fifth-generation Tensor Cores:\u003c\/strong\u003e up to 4,000 AI TOPS (FP4 with structured sparsity) and native FP4 support, a Blackwell capability that accelerates modern LLM inference and fine-tuning and is an architectural step beyond the previous RTX 6000 Ada generation.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003e188 fourth-generation RT Cores:\u003c\/strong\u003e hardware-accelerated ray and path tracing for production rendering, architectural visualization and real-time look development.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003e125 TFLOPS FP32:\u003c\/strong\u003e strong single-precision compute for CAD, simulation and scientific workloads.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003e600W configurable TDP:\u003c\/strong\u003e one 16-pin PCIe CEM5 power connector, with power tunable by system integrators to balance thermals, acoustics and density in workstation or server chassis.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eQuad DisplayPort 2.1b outputs:\u003c\/strong\u003e drive up to four high-resolution displays, including 8K panels, from one card.\u003c\/li\u003e\n\u003c\/ul\u003e\u003ch2\u003eSpecifications\u003c\/h2\u003e\u003ctable\u003e\n\u003cthead\u003e\u003ctr\u003e\n\u003cth\u003eSpec\u003c\/th\u003e\n\u003cth\u003eDetail\u003c\/th\u003e\n\u003c\/tr\u003e\u003c\/thead\u003e\n\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd\u003eArchitecture\u003c\/td\u003e\n\u003ctd\u003eNVIDIA Blackwell (GB202, full die), TSMC 4NP\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eCUDA Cores\u003c\/td\u003e\n\u003ctd\u003e24,064\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eTensor Cores\u003c\/td\u003e\n\u003ctd\u003e752 (5th-generation, native FP4)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eRT Cores\u003c\/td\u003e\n\u003ctd\u003e188 (4th-generation)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eMemory\u003c\/td\u003e\n\u003ctd\u003e96GB GDDR7 with ECC, 512-bit bus\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eMemory Bandwidth\u003c\/td\u003e\n\u003ctd\u003e1,792GB\/s\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eFP32 Compute\u003c\/td\u003e\n\u003ctd\u003e125 TFLOPS\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eAI Performance\u003c\/td\u003e\n\u003ctd\u003eUp to 4,000 AI TOPS (FP4 sparse)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003ePower\u003c\/td\u003e\n\u003ctd\u003e600W configurable TDP, 1x 16-pin PCIe CEM5 connector\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eInterface\u003c\/td\u003e\n\u003ctd\u003ePCIe 5.0 x16\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eDisplay Outputs\u003c\/td\u003e\n\u003ctd\u003e4x DisplayPort 2.1b\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eForm Factor\u003c\/td\u003e\n\u003ctd\u003eDual-slot, workstation blower\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eLaunch\u003c\/td\u003e\n\u003ctd\u003eMarch 2025, MSRP $8,565\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003c\/tbody\u003e\n\u003c\/table\u003e\u003ch2\u003eGood to know\u003c\/h2\u003e\u003cul\u003e\n\u003cli\u003eThis is a professional card, not a gaming GPU. It ships with NVIDIA’s Studio and RTX Enterprise driver branches and is validated against major CAD, DCC and AI frameworks.\u003c\/li\u003e\n\u003cli\u003eOne card with this much memory means no manual model sharding and no NVLink bridge management.\u003c\/li\u003e\n\u003cli\u003eAt 600W and dual-slot, it fits standard workstation chassis without the multi-card cooling and power demands of a datacenter GPU build.\u003c\/li\u003e\n\u003c\/ul\u003e\u003cp\u003eChoose this card when VRAM is your bottleneck: a language model that will not fit, a scene that keeps swapping to disk, or a simulation mesh you have had to decimate. It removes that ceiling in one upgrade.\u003c\/p\u003e","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":58232537481598,"sku":"NVIDIA-RTXPRO6000-96GB","price":13250.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1022\/4468\/0062\/files\/gpu-rtx-pro-6000_e1a9f438-abcb-4c56-bc89-ffbefc99805b.jpg?v=1792094031"},{"product_id":"nvidia-geforce-rtx-5090-founders-edition-32gb","title":"NVIDIA GeForce RTX 5090 Founders Edition (32GB)","description":"\u003cp\u003eThe NVIDIA GeForce RTX 5090 Founders Edition is NVIDIA’s flagship Blackwell-generation consumer GPU, the largest GeForce die NVIDIA has ever shipped, in a Founders Edition cooler engineered to fit that much silicon into two slots. It suits gamers and creators who refuse to compromise: native 4K at maximum settings, 8K footage editing, and local diffusion models and LLMs on your own hardware.\u003c\/p\u003e\n\u003ch2\u003eWho it's for\u003c\/h2\u003e\n\u003cul\u003e\n\u003cli\u003eNative 4K gaming with ray tracing maxed out, or high-refresh 1440p and 4K monitors\u003c\/li\u003e\n\u003cli\u003e8K video timelines, multi-layer compositing in DaVinci Resolve or Premiere, and large 3D scenes in Blender or Unreal Engine\u003c\/li\u003e\n\u003cli\u003eRunning Stable Diffusion and fine-tuning smaller LLMs locally\u003c\/li\u003e\n\u003cli\u003eInference on quantized 30B-class models that would spill to system RAM on a 24GB card\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003ch2\u003eKey features\u003c\/h2\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003e21,760 CUDA cores:\u003c\/strong\u003e the largest GeForce GPU configuration NVIDIA has produced, on a custom TSMC 4NP process, a substantial generational leap over the RTX 4090 (21,760 vs 16,384 cores).\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003e32GB GDDR7 on a 512-bit bus:\u003c\/strong\u003e memory capacity and bandwidth for 4K\/8K textures, huge open-world scenes and local AI models that would choke a 24GB card.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003e98MB L2 cache:\u003c\/strong\u003e an expanded cache hierarchy that keeps the compute cores fed and reduces trips to memory.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003e680 fifth-generation Tensor Cores:\u003c\/strong\u003e up to 3,352 AI TOPS, powering DLSS 4.5 with Multi Frame Generation for much higher frame rates at native-quality image fidelity.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003e170 fourth-generation RT Cores:\u003c\/strong\u003e full-scene path tracing in supported titles without the frame-rate penalty older RT hardware imposed.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003e104.8 TFLOPS FP32 shader compute:\u003c\/strong\u003e a generational jump in raw rasterization and compute throughput over Ada Lovelace.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003e2.41GHz boost clock:\u003c\/strong\u003e high clocks despite the core count, thanks to the refined 4NP process node.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eNVENC\/NVDEC with AV1 support:\u003c\/strong\u003e cuts export and streaming times significantly versus CPU-only workflows.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eCompact 2-slot Founders Edition design:\u003c\/strong\u003e vapor-chamber cooling and flow-through design, validated as a matched pair with the card’s power delivery, in a footprint that fits SFF and standard ATX builds, unlike the triple-slot coolers common on partner cards this powerful.\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003ch2\u003eSpecifications\u003c\/h2\u003e\n\u003ctable\u003e\n\u003cthead\u003e\u003ctr\u003e\n\u003cth\u003eSpec\u003c\/th\u003e\n\u003cth\u003eDetail\u003c\/th\u003e\n\u003c\/tr\u003e\u003c\/thead\u003e\n\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd\u003eArchitecture\u003c\/td\u003e\n\u003ctd\u003eNVIDIA Blackwell, TSMC 4NP\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eCUDA cores\u003c\/td\u003e\n\u003ctd\u003e21,760\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eTensor Cores\u003c\/td\u003e\n\u003ctd\u003e680 (5th-generation)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eRT Cores\u003c\/td\u003e\n\u003ctd\u003e170 (4th-generation)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eMemory\u003c\/td\u003e\n\u003ctd\u003e32GB GDDR7, 512-bit bus, 98MB L2 cache\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eFP32 compute\u003c\/td\u003e\n\u003ctd\u003e~104.8 TFLOPS\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eAI performance\u003c\/td\u003e\n\u003ctd\u003eUp to 3,352 AI TOPS\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eBoost clock\u003c\/td\u003e\n\u003ctd\u003e2.41GHz\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eTotal graphics power\u003c\/td\u003e\n\u003ctd\u003e575W\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003ePower connector\u003c\/td\u003e\n\u003ctd\u003e1x 16-pin (12V-2×6)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eInterface\u003c\/td\u003e\n\u003ctd\u003ePCIe 5.0\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eDisplay outputs\u003c\/td\u003e\n\u003ctd\u003eDisplayPort 2.1b, up to 8K @ 165Hz\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eRecommended PSU\u003c\/td\u003e\n\u003ctd\u003e1000W\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eLaunch\u003c\/td\u003e\n\u003ctd\u003eJanuary 2025, MSRP $1,999\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003c\/tbody\u003e\n\u003c\/table\u003e\n\u003ch2\u003eGood to know\u003c\/h2\u003e\n\u003cul\u003e\n\u003cli\u003eTotal graphics power is 575W, so a capable 1000W PSU and a case with good airflow are non-negotiable.\u003c\/li\u003e\n\u003cli\u003eFor local AI it will not match a dedicated 96GB workstation card on the largest models, but for generative AI alongside gaming and creative work no other consumer GPU offers this much memory and compute in one card.\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003cp\u003eChoose the RTX 5090 when you want the most capable GPU NVIDIA has put in a GeForce box and have the power supply and airflow to match. If 24GB of memory is enough for you, the RTX 4090 is the other option.\u003c\/p\u003e","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":58232537514366,"sku":"NVIDIA-RTX5090-FE","price":1999.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1022\/4468\/0062\/files\/gpu-rtx-5090_10f6e9ed-a914-4145-a3a4-fbfe6cf0ce27.jpg?v=1792094032"},{"product_id":"nvidia-geforce-rtx-4090-founders-edition-24gb","title":"NVIDIA GeForce RTX 4090 Founders Edition (24GB)","description":"\u003cp\u003eThe NVIDIA GeForce RTX 4090 Founders Edition is the Ada Lovelace flagship, and two-plus years after launch it still holds its own against everything short of NVIDIA’s newest Blackwell generation. It suits gamers who want maxed-out 4K performance, creators pushing 8K video and large 3D scenes, and enthusiasts running local AI models.\u003c\/p\u003e\n\u003ch2\u003eWho it's for\u003c\/h2\u003e\n\u003cul\u003e\n\u003cli\u003eNative 4K gaming with ray tracing, and high-refresh 1440p with plenty of headroom\u003c\/li\u003e\n\u003cli\u003e8K video editing, dense Blender and Unreal Engine scenes and multi-layer compositing\u003c\/li\u003e\n\u003cli\u003eRunning Stable Diffusion and similar image models at full speed in 24GB\u003c\/li\u003e\n\u003cli\u003eInference on quantized LLMs in the 13B–34B parameter range without exotic offloading tricks\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003ch2\u003eKey features\u003c\/h2\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003e16,384 CUDA cores:\u003c\/strong\u003e massive parallel compute on a custom TSMC 4N process, still enough to lead every non-Blackwell GPU in raw shader throughput.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003e24GB GDDR6X on a 384-bit bus:\u003c\/strong\u003e 21Gbps for over 1TB\/s of memory bandwidth, handling 4K\/8K textures, large open-world scenes and local AI models up to the mid-teens in billions of parameters.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003e72MB L2 cache:\u003c\/strong\u003e a large on-die cache that reduces memory-bound stalls in games and compute workloads.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003e512 fourth-generation Tensor Cores:\u003c\/strong\u003e up to 1,321 AI TOPS, driving DLSS 3 Frame Generation and local inference for Stable Diffusion, LLMs and other generative AI.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003e128 third-generation RT Cores:\u003c\/strong\u003e up to 191 TFLOPS of ray tracing performance for fully path-traced titles like Cyberpunk 2077 and Alan Wake 2.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003e82.6 TFLOPS FP32 shader compute:\u003c\/strong\u003e a substantial generational gain over the previous RTX 30-series flagship, still highly competitive today.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003e2.52GHz boost clock:\u003c\/strong\u003e high out-of-the-box clocks with overclocking headroom on partner and Founders Edition boards alike.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eAV1 hardware encode and decode:\u003c\/strong\u003e high-quality hardware video encoding that cuts export times and improves streaming quality versus older codecs.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eFounders Edition cooler:\u003c\/strong\u003e NVIDIA’s own dual-axial-flow cooler and vapor chamber design keeps the 450W TDP in check without the bulk of some triple-slot partner cards.\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003ch2\u003eSpecifications\u003c\/h2\u003e\n\u003ctable\u003e\n\u003cthead\u003e\u003ctr\u003e\n\u003cth\u003eSpec\u003c\/th\u003e\n\u003cth\u003eDetail\u003c\/th\u003e\n\u003c\/tr\u003e\u003c\/thead\u003e\n\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd\u003eArchitecture\u003c\/td\u003e\n\u003ctd\u003eNVIDIA Ada Lovelace, TSMC 4N\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eCUDA cores\u003c\/td\u003e\n\u003ctd\u003e16,384\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eTensor Cores\u003c\/td\u003e\n\u003ctd\u003e512 (4th-generation)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eRT Cores\u003c\/td\u003e\n\u003ctd\u003e128 (3rd-generation)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eMemory\u003c\/td\u003e\n\u003ctd\u003e24GB GDDR6X, 384-bit bus, 21Gbps, 72MB L2 cache\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eMemory bandwidth\u003c\/td\u003e\n\u003ctd\u003e~1,008GB\/s\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eFP32 compute\u003c\/td\u003e\n\u003ctd\u003e82.6 TFLOPS\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eAI performance\u003c\/td\u003e\n\u003ctd\u003eUp to 1,321 AI TOPS\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eBoost clock\u003c\/td\u003e\n\u003ctd\u003e2.52GHz\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eTotal graphics power\u003c\/td\u003e\n\u003ctd\u003e450W (transient spikes up to 600W)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eInterface\u003c\/td\u003e\n\u003ctd\u003ePCIe 4.0 x16\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eDisplay outputs\u003c\/td\u003e\n\u003ctd\u003eDisplayPort 1.4a, HDMI 2.1a\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eRecommended PSU\u003c\/td\u003e\n\u003ctd\u003e850W\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eLaunch\u003c\/td\u003e\n\u003ctd\u003eOctober 2022, original MSRP $1,599\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003c\/tbody\u003e\n\u003c\/table\u003e\n\u003ch2\u003eGood to know\u003c\/h2\u003e\n\u003cul\u003e\n\u003cli\u003ePair it with an 850W-or-better power supply and a case with decent airflow. The card is known for transient power spikes of up to 600W.\u003c\/li\u003e\n\u003cli\u003eAt native 4K with ray tracing enabled it delivers high, stable frame rates in demanding current titles, and DLSS 3 Frame Generation extends that lead in supported games.\u003c\/li\u003e\n\u003cli\u003eThe NVENC AV1 encoder significantly speeds up exports and live streaming versus CPU-based encoding or older hardware encoders.\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003cp\u003eChoose the RTX 4090 for uncompromising 4K gaming, creative work and local AI without stepping up to Blackwell pricing. Only NVIDIA’s newest Blackwell flagships outrun it.\u003c\/p\u003e","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":58232537547134,"sku":"NVIDIA-RTX4090-FE","price":1599.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1022\/4468\/0062\/files\/gpu-rtx-4090_ca2528f4-691c-4fd1-962b-45a9b462ecf9.jpg?v=1792094034"}],"url":"https:\/\/computahardware.net\/collections\/nvidia.oembed","provider":"ComputaHardware","version":"1.0","type":"link"}