NVIDIA GB200 NVL72 Rack-Scale AI Accelerator
Brand: NVIDIA | Category: GPUs
SKU: 900-21010-0210-000 | Part #: 900-21010-0210-000 | MPN: 900-21010-0210-000
Contact for Pricing — Request a Quote
About the NVIDIA GB200 NVL72 Rack-Scale AI Accelerator
NVIDIA datacentre GPU (B200) for large-language-model training, inference, and HPC workloads. Stocked through authorised channels.
At a glance — key specifications
Perfect for
- LLM training (GPT, Llama, Falcon, DeepSeek scale)
- Inference farms and RAG infrastructure
- High-performance computing (CFD, weather, genomics)
- Visualisation and rendering farms
- Scientific / academic research clusters
Why buy the NVIDIA GB200 NVL72 Rack-Scale AI Accelerator from Omnixon Global
- Authorised distribution only — 100% authentic NVIDIA hardware, serial-number registrable, warranty processes cleanly with the manufacturer.
- Dubai-based logistics hub — same-day delivery within Dubai for in-stock SKUs, courier-cleared delivery across UAE, Saudi Arabia, Qatar, Kuwait, Oman, Bahrain, plus broader EMEA + APAC.
- 24-hour RFQ turn-around — submit your part numbers and quantities, get channel-direct pricing and confirmed availability the next business day.
- Pre-sales engineering on call — multilingual (English / Arabic / Persian / Russian) pre-sales engineers help with sizing, configuration, BOM validation, and compatibility checks at no charge.
- Post-sale support attach — manufacturer support contracts (Dell ProSupport, HPE Foundation Care, Lenovo Premier, Cisco SmartNet, Aruba Care, Juniper J-Care) bundled at quote time.
- Worldwide shipping — air, sea, courier express, with all customs documentation handled by our logistics team.
Frequently asked questions
What server platforms accept the NVIDIA GB200 NVL72 Rack-Scale AI Accelerator?
Reference servers include Dell PowerEdge XE9680 / XE9712, HPE Cray XD670, Lenovo ThinkSystem SR685a / SR675 V3, Supermicro AS-A21GE / SYS-821GE, Gigabyte G593 / G894, ASUS ESC. Share your target platform in the RFQ and we will confirm chassis-to-GPU compatibility and recommended NIC pairing.
How long is the lead time on AI GPUs?
Highly model-dependent. L40S / RTX-class: typically 3-6 weeks. H100/H200/B200 in SXM form factor: 12-16 weeks for whole-platform allocations. We quote authorised-channel ETAs only — no grey-market promises.
Do you supply matched networking (Quantum InfiniBand / Spectrum-X)?
Yes — Omnixon stocks the full NVIDIA networking lineup (Quantum-2 / Quantum-X InfiniBand, Spectrum-X Ethernet, ConnectX NICs, BlueField DPUs) so we can quote a complete training-cluster BOM, not just the GPUs.
Can you help with NVIDIA AI Enterprise licensing?
Yes. We hold authorised channels for NVIDIA AI Enterprise software subscriptions. Add it to your RFQ and we quote node-aligned licensing along with the hardware.
Request a quote for the NVIDIA GB200 NVL72 Rack-Scale AI Accelerator
Submit your quantity, destination country, and required lead time below. Our pre-sales team responds within 24 business hours with confirmed channel pricing, availability, and matching support contract options.
Request a Quote →Product information is provided for B2B procurement guidance. Pricing and availability subject to vendor confirmation at quote time. All trademarks are property of their respective owners. Omnixon Global is an independent authorised reseller — not affiliated with the manufacturer.
Technical Specifications
| Brand | NVIDIA |
| Category | GPUs |
| SKU | 900-21010-0210-000 |
| Part Number | 900-21010-0210-000 |
| Condition | New |
| GPU Model | B200 |
| Power Connector | 12V-2x6 / 16-pin (server-class) |
| Warranty | 3-year manufacturer warranty (extended available) |
| Manufacturer Part Number | 900-21010-0210-000 |
| Form Factor | Rack-scale integrated system |
| GPU Configuration | 2 x Blackwell GPUs + 2 x Grace CPUs |
| Aggregate GPU Memory | 288 GB HBM3e |
| Interconnect Bandwidth | 900 GB/s (NVLink) |
| CPU Memory | 96 GB LPDDR5X |
| FP8 Tensor Performance (aggregate) | 37.8 TFLOPS per GPU |
| Power Consumption | 1440 W total TDP |
| Network Interface | Dual 400GbE or higher |
| Operating Temperature | 0–50°C |
| Cooling Type | Liquid-cooled design |
Frequently Asked Questions about NVIDIA GB200 NVL72 Rack-Scale AI Accelerator
What server platforms accept the NVIDIA GB200 NVL72 Rack-Scale AI Accelerator?
Reference servers include Dell PowerEdge XE9680 / XE9712, HPE Cray XD670, Lenovo ThinkSystem SR685a / SR675 V3, Supermicro AS-A21GE / SYS-821GE, Gigabyte G593 / G894, ASUS ESC. Share your target platform in the RFQ and we will confirm chassis-to-GPU compatibility and recommended NIC pairing.
How long is the lead time on AI GPUs?
Highly model-dependent. L40S / RTX-class: typically 3-6 weeks. H100/H200/B200 in SXM form factor: 12-16 weeks for whole-platform allocations. We quote authorised-channel ETAs only — no grey-market promises.
Do you supply matched networking (Quantum InfiniBand / Spectrum-X)?
Yes — Omnixon stocks the full NVIDIA networking lineup (Quantum-2 / Quantum-X InfiniBand, Spectrum-X Ethernet, ConnectX NICs, BlueField DPUs) so we can quote a complete training-cluster BOM, not just the GPUs.
Can you help with NVIDIA AI Enterprise licensing?
Yes. We hold authorised channels for NVIDIA AI Enterprise software subscriptions. Add it to your RFQ and we quote node-aligned licensing along with the hardware.