Brand: AMD | Category: GPUs
SKU: 100-300000087 | Part #: 100-300000087 | MPN: 100-300000087
Contact for Pricing — Request a Quote
The AMD Radeon Pro W7900DS is a dual-slot, actively cooled workstation GPU designed for demanding professional compute and visualization workloads. Built on AMD's RDNA 3 architecture with the Navi 31 GPU core, this card delivers 6,144 stream processors across 96 compute units, achieving approximately 61.3 TFLOPS of peak FP32 compute performance. The 48 GB GDDR6 memory pool connects via a 384-bit memory interface, providing the bandwidth and capacity required for large-scale data processing, scientific simulation, and complex rendering tasks. The card interfaces with host systems through PCIe 4.0 x16 and draws 260 W typical power, requiring dual 8-pin connectors for stable operation.
Workstation administrators, data center architects, and professional visualization teams choose the W7900DS for its proven support across critical software ecosystems. AMD's Radeon Pro professional driver ISV certification program ensures compatibility with industry-standard applications, while native support for DirectX 12 Ultimate, Vulkan 1.3, OpenGL 4.6, and OpenCL 2.0 enables seamless integration into existing pipelines. ROCm support opens additional pathways for high-performance computing, machine learning, and heterogeneous processing. The six DisplayPort 2.1 outputs allow simultaneous connection of up to six displays, making the W7900DS ideal for multi-monitor professional workflows. Windows 10/11 (64-bit) and Linux operating systems are both supported, delivering flexibility across enterprise environments.
Part number 100-300000087 represents a significant investment in professional-grade GPU infrastructure. Omnixon Global maintains direct relationships with AMD and regional distributors to ensure availability, technical support, and warranty compliance for enterprises across the UAE and MENA region. To discuss pricing, stock status, volume licensing, and integration support for your deployment, please submit a detailed Request for Quote through our team.
| Brand | AMD |
| Category | GPUs |
| SKU | 100-300000087 |
| Part Number | 100-300000087 |
| Condition | New |
| Manufacturer Part Number | 100-300000087 |
| GPU Architecture | RDNA 3 (Navi 31) |
| Form Factor | Dual Slot |
| Memory Capacity | 48 GB GDDR6 |
| Memory Interface Width | 384-bit |
| Compute Units | 96 |
| Stream Processors | 6144 |
| Peak FP32 Compute | Approximately 61.3 TFLOPS |
| Display Outputs | 6x DisplayPort 2.1 |
| Maximum Displays Supported | 6 |
| PCIe Interface | PCIe 4.0 x16 |
| Typical Board Power | 260 W |
| Power Connectors | 2x 8-pin |
| API Support | DirectX 12 Ultimate, Vulkan 1.3, OpenGL 4.6, OpenCL 2.0 |
| ROCm Support | Yes |
| ISV Certifications | AMD Radeon Pro professional driver ISV certification program |
| Operating System Support | Windows 10/11 (64-bit), Linux |
| Slot Width | Dual Slot |
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 genuine-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 genuine-channels for NVIDIA AI Enterprise software subscriptions. Add it to your RFQ and we quote node-aligned licensing along with the hardware.