
NVIDIA HGX B200 8-GPU Platform
Eight Blackwell GPUs with 1.4 TB of HBM3e for large-scale AI training and inference
InTechnologies FZCO supplies NVIDIA products to business buyers: marketplace sellers, retailers, system integrators and corporate IT teams. Select the items you need, set quantities and send one quote request; we reply with availability, lead time and landed cost to your destination.
Products shown: 16

Eight Blackwell GPUs with 1.4 TB of HBM3e for large-scale AI training and inference

Eight Blackwell Ultra GPUs with 2.1 TB of HBM3e for reasoning-model inference at scale

Turnkey 10U AI system with eight Blackwell GPUs, 1.4 TB HBM3e and 72 PFLOPS FP8 training

Dual-slot Blackwell workstation GPU with 48 GB ECC GDDR7 and 14,080 CUDA cores

Pulled Ampere accelerator with 80 GB HBM2e, tested under load and supplied after end-user verification

Liquid-cooled rack with 72 Blackwell GPUs and 36 Grace CPUs in one 130 TB/s NVLink domain

PCIe Hopper GPU with 141 GB HBM3e and 4-way NVLink bridging for air-cooled servers

Dual-slot PCIe Hopper GPU with 94 GB HBM3 and NVLink bridge support for LLM inference

Passively cooled 96 GB GDDR7 Blackwell GPU for inference, rendering and vGPU in servers

Desktop Blackwell GPU with 96 GB GDDR7 ECC, 4,000 AI TOPS and four DisplayPort 2.1 outputs

Universal 48 GB Ada Lovelace GPU for inference, fine-tuning, graphics and video

200 W dual-slot workstation GPU with 32 GB ECC GDDR7 and 10,496 CUDA cores

Complete used 4U system with eight A100 SXM4 GPUs on an NVSwitch baseboard, 640 GB of HBM2e

Hopper accelerator with FP8 Transformer Engine and 80 GB HBM2e, pulled from cluster service and tested

Ampere workstation card with 48 GB of ECC GDDR6, pulled from render and visualisation systems and tested

Ada Lovelace flagship with 16,384 CUDA cores and 24 GB GDDR6X, tested partner cards from used systems