Intel Data Center GPU Flex 170 PCIe 16GB GDDR6
Brand: Intel | Category: GPUs
SKU: XPGEDCGPUF170 | Part #: XPGEDCGPUF170 | MPN: XPGEDCGPUF170
Contact for Pricing — Request a Quote
About the Intel Data Center GPU Flex 170 PCIe 16GB GDDR6
The Intel Data Center GPU Flex 170 PCIe 16GB GDDR6 delivers 16 GB of GDDR6 memory across a 256-bit memory interface, providing the bandwidth and capacity needed for demanding data center workloads. Built on the Intel Xe-HP architecture with 512 execution units and 32 Xe-Cores, this GPU accelerator is engineered for real-time video processing, AI inference, and virtualized graphics scenarios across enterprise environments. The (XPGEDCGPUF170) combines dual hardware encode and decode engines with support for AV1, HEVC, AVC, and VP9 formats, making it ideal for media transcoding and streaming applications at scale.
This PCIe 4.0 x16 add-in card integrates an active cooling solution and operates at 150 W TDP, fitting seamlessly into standard data center chassis. Virtualization support via SR-IOV enables flexible resource sharing across multiple virtual machines, while comprehensive API support including oneAPI, SYCL, and OpenCL ensures broad software compatibility. For IT procurement teams and infrastructure architects deploying video analytics, transcoding, or inference workloads, the Intel Data Center GPU Flex 170 offers proven reliability and native Linux support. The 7680 x 4320 maximum resolution capability extends use cases into 8K content processing. Contact Omnixon Global today to request a quotation for the Intel Data Center GPU Flex 170 and explore volume pricing options for your deployment.
Key Specifications
- Manufacturer: Intel
- Part Number: XPGEDCGPUF170
- GPU Architecture: Intel Xe-HP
- Memory: 16 GB GDDR6 with 256-bit interface
- Host Interface: PCIe 4.0 x16
- Power Consumption: 150 W TDP with 1x 8-pin PCIe power connector
- Encoding/Decoding: 2 hardware encode engines and 2 hardware decode engines supporting AV1, HEVC, AVC, and VP9
- Virtualization: SR-IOV support
- API Support: oneAPI, SYCL, OpenCL, Intel Media SDK
- Maximum Resolution: 7680 x 4320
Technical Specifications
| Brand | Intel |
| Category | GPUs |
| SKU | XPGEDCGPUF170 |
| Part Number | XPGEDCGPUF170 |
| Condition | New |
| Manufacturer Part Number | XPGEDCGPUF170 |
| GPU Architecture | Intel Xe-HP |
| Memory Capacity | 16 GB GDDR6 |
| Memory Interface Width | 256-bit |
| Form Factor | PCIe Add-in Card (AIC) |
| Host Interface | PCIe 4.0 x16 |
| TDP | 150 W |
| Execution Units | 512 |
| Xe-Cores | 32 |
| Hardware Decode Engines | 2 |
| Hardware Encode Engines | 2 |
| Supported Encode/Decode Formats | AV1, HEVC (H.265), AVC (H.264), VP9 |
| Virtualization Support | SR-IOV |
| API Support | oneAPI, SYCL, OpenCL, Intel Media SDK |
| Operating System Support | Linux (select distributions) |
| Cooling | Active (integrated fan) |
| Power Connector | 1x 8-pin PCIe |
| Max Resolution | 7680 x 4320 (8K) |
Frequently Asked Questions about Intel Data Center GPU Flex 170 PCIe 16GB GDDR6
What server platforms accept the Intel Data Center GPU Flex 170 PCIe 16GB GDDR6?
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.
How long is the lead time on AI GPUs?
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.
Do you supply matched networking (Quantum InfiniBand / Spectrum-X)?
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.
Can you help with NVIDIA AI Enterprise licensing?
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.