Brand: HPE | Category: GPUs
SKU: P67211-B21 | Part #: P67211-B21 | MPN: P67211-B21
Contact for Pricing — Request a Quote
The NVIDIA RTX 4000 Ada Generation 20GB PCIe GPU, offered by HPE under part number P67211-B21, is purpose-built for HPE Z-series workstations and delivers professional-grade graphics and compute performance on the Ada Lovelace architecture. Featuring 6,144 CUDA cores, third-generation RT cores for real-time ray tracing, and fourth-generation Tensor cores purpose-built for AI inferencing and deep learning tasks, this GPU represents a significant generational leap in workstation-class compute density.
With 20GB of ECC-protected GDDR6 memory on a 160-bit memory bus, the RTX 4000 Ada provides the memory headroom required for large dataset visualization, complex simulation environments, and multi-application professional workflows. The card operates within a 130W TDP envelope, making it compatible with single-slot power configurations in supported Z-series workstation chassis without requiring supplemental PCIe power connectors, simplifying deployment in managed enterprise environments.
Designed to meet the demands of enterprise IT infrastructure teams deploying standardized professional workstation fleets, the RTX 4000 Ada carries NVIDIA RTX Enterprise software support, including access to NVIDIA vWS (virtual workstation) capabilities, ISV certifications across leading CAD, simulation, and media applications, and compatibility with HPE's integrated workstation management ecosystem. Its low-profile-compatible form factor and validated HPE qualification make it a compelling option for organizations in sectors such as engineering, life sciences, media production, and AI-assisted analytics.
| Manufacturer | HPE |
| Manufacturer Part Number | P67211-B21 |
| GPU Architecture | NVIDIA Ada Lovelace |
| CUDA Cores | 6,144 |
| RT Cores | 48 (3rd Generation) |
| Tensor Cores | 192 (4th Generation) |
| GPU Memory | 20GB GDDR6 |
| Memory Interface | 160-bit |
| ECC Memory Support | Yes |
| Memory Bandwidth | 360 GB/s |
| TDP (Thermal Design Power) | 130W |
| External Power Connector | None required |
| Form Factor | Full-height, single-slot |
| PCIe Interface | PCIe 4.0 x16 |
| Display Outputs | 4x DisplayPort 1.4a |
| Maximum Display Resolution | 7680 x4320 (8K) |
| DirectX Support | DirectX 12 Ultimate |
| OpenGL Support | OpenGL 4.6 |
| Vulkan Support | Vulkan 1.3 |
| NVENC / NVDEC | Yes (8th Gen Encoder / 5th Gen Decoder) |
| Compatible Platforms | HPE Z-series Workstations |
| Operating System Support | Windows 10/11 (64-bit), Red Hat Enterprise Linux, Ubuntu LTS |
Available from Omnixon Global. Submit an RFQ and our team will confirm configuration and availability for your order.
| Brand | HPE |
| Category | GPUs |
| SKU | P67211-B21 |
| Part Number | P67211-B21 |
| Condition | New |
| Manufacturer Part Number | P67211-B21 |
| GPU Architecture | NVIDIA Ada Lovelace |
| CUDA Cores | 6,144 |
| RT Cores | 48 (3rd Generation) |
| Tensor Cores | 192 (4th Generation) |
| GPU Memory | 20GB GDDR6 |
| Memory Interface | 160-bit |
| ECC Memory Support | Yes |
| Memory Bandwidth | 360 GB/s |
| TDP (Thermal Design Power) | 130W |
| External Power Connector | None required |
| Form Factor | Full-height, single-slot |
| PCIe Interface | PCIe 4.0 x16 |
| Display Outputs | 4x DisplayPort 1.4a |
| Maximum Display Resolution | 7680 x4320 (8K) |
| DirectX Support | DirectX 12 Ultimate |
| OpenGL Support | OpenGL 4.6 |
| Vulkan Support | Vulkan 1.3 |
| NVENC / NVDEC | Yes (8th Gen Encoder / 5th Gen Decoder) |
| Compatible Platforms | HPE Z-series Workstations |
| Operating System Support | Windows 10/11 (64-bit), Red Hat Enterprise Linux, Ubuntu LTS |
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.