Brand: Intel | Category: GPUs
SKU: 21P73K | Part #: 21P73K | MPN: 21P73K
Contact for Pricing — Request a Quote
The Intel Arc Pro A60 PCIe Workstation GPU delivers professional-grade compute performance across multiple AI precision points, with support for FP32, BF16, and FP8/INT8 workloads through its 28 Xe-Cores and 224 XMX AI Engines. This 12GB GDDR6 accelerator combines Intel's Xe-HPG architecture with 28 dedicated Ray Tracing Units, making it a versatile platform for demanding workstation applications in content creation, scientific simulation, and professional visualization. Whether you are an AI infrastructure team optimizing model training pipelines or a CAD/DCC professional seeking certified hardware acceleration, the Arc Pro A60 (part number 21P73K) integrates seamlessly into existing PCIe 4.0 x16 systems running Windows 10/11 64-bit or Linux environments.
Built on Intel's compute framework ecosystem, the Arc Pro A60 supports Intel oneAPI, SYCL, and OpenCL, alongside industry-standard APIs including DirectX 12 Ultimate, Vulkan 1.3, and OpenGL 4.6. The GPU features comprehensive video encode and decode capabilities for AV1, HEVC, and H.264 formats, reducing bottlenecks in media workflows. Its four DisplayPort 2.0 outputs drive up to 4K simultaneous displays at resolutions up to 7680 x 4320 (8K), ideal for multi-monitor professional setups. Intel has certified the Arc Pro A60 for professional CAD and DCC applications, ensuring reliability across industry-standard software stacks. Contact the Omnixon Global team to request a formal quotation for the Intel Arc Pro A60 and explore volume licensing options.
| Brand | Intel |
| Category | GPUs |
| SKU | 21P73K |
| Part Number | 21P73K |
| Condition | New |
| Manufacturer Part Number | 21P73K |
| GPU Architecture | Xe-HPG |
| Xe-Cores | 28 |
| Ray Tracing Units | 28 |
| XMX AI Engines | 224 |
| Memory Capacity | 12 GB GDDR6 |
| Memory Interface Width | 192-bit |
| PCIe Interface | PCIe 4.0 x16 |
| API Support | DirectX 12 Ultimate, OpenCL 3.0, Vulkan 1.3, OpenGL 4.6 |
| Compute Framework Support | Intel oneAPI, SYCL, OpenCL |
| Video Encode/Decode | AV1 Hardware Encode & Decode, HEVC, H.264 |
| Display Outputs | 4x DisplayPort 2.0 |
| Maximum Display Resolution | 7680 x 4320 (8K) |
| Maximum Simultaneous Displays | 4 |
| Form Factor | PCIe Add-In Card |
| ISV Certifications | Professional application ISV-certified (CAD, DCC) |
| Operating System Support | Windows 10/11 64-bit, Linux |
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.