Brand: Intel | Category: GPUs
SKU: 21P73G | Part #: 21P73G | MPN: 21P73G
Contact for Pricing — Request a Quote
PCIe 4.0 x8 interface and 50W TDP determine server chassis and PSU compatibility, making the Intel Arc Pro A40 (part number 21P73G) a power-efficient addition to existing workstation infrastructure without auxiliary power requirements. This single-slot, low-profile GPU delivers professional-grade compute acceleration through Intel's Xe-HPG architecture, featuring 6 Xe-Cores, 6 ray tracing units, and 96 XMX AI engines paired with 6GB GDDR6 memory on a 96-bit interface. Memory bandwidth reaches 96 GB/s, enabling smooth handling of complex visualization and compute workloads. The card supports four Mini DisplayPort 2.0 outputs capable of 7680x4320 (8K) resolution, ideal for multi-monitor professional workflows.
Intel engineered the Arc Pro A40 for visualization specialists, CAD professionals, and rendering teams requiring certified ISV support across professional applications. The GPU implements comprehensive codec support—AV1, HEVC (H.265), and H.264 hardware encode and decode—alongside Intel oneAPI compute frameworks and multi-API compatibility including DirectX 12 Ultimate, Vulkan, OpenCL 3.0, and OpenGL 4.6. Its 50W power envelope and elimination of external connectors simplify deployment in space-constrained server environments. IT procurement teams standardizing on Intel Arc Pro acceleration will find 21P73G delivers production-ready performance for CAD, visualization, and professional content creation without infrastructure redesign. Contact Omnixon Global to discuss your GPU acceleration requirements and request a quotation.
| Brand | Intel |
| Category | GPUs |
| SKU | 21P73G |
| Part Number | 21P73G |
| Condition | New |
| Manufacturer Part Number | 21P73G |
| Product Name | Intel Arc Pro A40 |
| GPU Architecture | Intel Xe-HPG |
| Xe-Cores | 6 |
| Ray Tracing Units | 6 |
| XMX AI Engines | 96 |
| Video Memory | 6GB GDDR6 |
| Memory Interface Width | 96-bit |
| Memory Bandwidth | 96 GB/s |
| PCIe Interface | PCIe 4.0 x8 |
| Display Outputs | 4x Mini DisplayPort 2.0 |
| Maximum Display Resolution | 7680x4320 (8K) |
| API Support | DirectX 12 Ultimate, Vulkan, OpenCL 3.0, OpenGL 4.6 |
| Compute API | Intel oneAPI |
| Hardware Video Encode/Decode | AV1, HEVC (H.265), H.264 hardware encode and decode |
| Thermal Design Power (TDP) | 50W |
| Auxiliary Power Connector | None required |
| Form Factor | Single-slot, low-profile capable |
| ISV Certifications | Professional application ISV certifications (CAD, visualization) |
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.