Brand: NVIDIA | Category: GPUs
SKU: NVI-900-21010-0040-000 | Part #: 900-21010-0040-000 | MPN: 900-21010-0040-000
Contact for Pricing — Request a Quote
The NVIDIA 900-21010-0040-000 H200 NVL is a full-height, dual-slot GPU engineered for next-generation AI, machine learning, and high-performance computing workloads. This enterprise-class accelerator delivers exceptional computational density and memory throughput, making it the ideal choice for AI infrastructure teams and data center architects tasked with deploying large-scale language models and complex simulation environments.
Built on NVIDIA's latest architecture, the H200 NVL combines 141 GB of HBM3e memory with an industry-leading 4.8 TB/s memory bandwidth, enabling rapid data movement between compute and storage layers. With peak tensor performance reaching 141 TFLOPS (TF32) and peak FP8 performance of 49.1 TFLOPS, this GPU accelerates mixed-precision inference and training at scale. The card connects via PCIe 5.0 and features NVLink 4.0 with 8x connections for ultra-low-latency multi-GPU communication. Rated for 700 W typical power consumption and supported by a 3-year manufacturer warranty—with extended coverage available—the H200 operates reliably across the full industrial temperature range of 0–85°C. A dual 12V-2x6 16-pin server-class power connector ensures seamless integration into existing enterprise infrastructure.
For enterprise procurement inquiries regarding NVIDIA GPU solutions, contact Omnixon Global for a detailed RFQ.
```| Brand | NVIDIA |
| Category | GPUs |
| SKU | NVI-900-21010-0040-000 |
| Part Number | 900-21010-0040-000 |
| Condition | New |
| Capacity | 141GB |
| Interface | PCIe 5.0 x16 |
| GPU Model | H200 |
| Power Connector | 12V-2x6 / 16-pin (server-class) |
| Warranty | 3-year manufacturer warranty (extended available) |
| Manufacturer Part Number | 900-21010-0040-000 |
| Memory | 141 GB HBM3e |
| Memory Bandwidth | 4.8 TB/s |
| Peak FP8 Performance | 49.1 TFLOPS |
| Peak Tensor Performance | 141 TFLOPS (TF32) |
| Interface | PCIe 5.0 |
| NVLink | NVLink 4.0 (8x connection) |
| Power Consumption | 700 W typical |
| Form Factor | Full-height, dual-slot |
| Operating Temperature | 0–85°C |
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.
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.
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.
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.