Brand: NVIDIA | Category: GPUs
SKU: 900-21010-0080-100 | Part #: 900-21010-0080-100 | MPN: 900-21010-0080-100
Contact for Pricing — Request a Quote
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.
Yes — Omnixon supplies 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.
Submit your quantity, destination country, and required lead time below. Our pre-sales team responds within 48 hours with confirmed competitive quoting, availability, and matching support contract options.
Request a Quote →Product information is provided for B2B procurement guidance. All trademarks are property of their respective owners.
| Brand | NVIDIA |
| Category | GPUs |
| SKU | 900-21010-0080-100 |
| Part Number | 900-21010-0080-100 |
| Condition | New |
| GPU Memory | 80 GB |
| Memory Type | HBM2e |
| Form Factor / Interconnect | SXM5 |
| Power Connector | 12V-2x6 / 16-pin (server-class) |
| Manufacturer Part Number | 900-21010-0080-100 |
| GPU Memory Capacity | 80 GB |
| Form Factor | SXM5 |
| Memory Bandwidth | 2.4 TB/s |
| Tensor Performance (TF32) | 1,979 TFLOPS |
| Tensor Performance (FP64) | 989 TFLOPS |
| NVLink Interconnect | SXM5 NVLink 3.0 |
| Typical Power Consumption | 700W |
| Workload Support | LLM training, inference, HPC |
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.
Yes — Omnixon supplies 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.
