HPE Compute XD690
A 10U air-cooled single-node chassis carrying eight NVIDIA Blackwell Ultra SXM6 GPUs on the HGX B300 baseboard, which HPE names directly in the orderable part S6A37A. Two Intel Xeon 6 processors with P-cores drive it, either the 6776P or the 6767P, both 64-core at 350 W, with up to 32 DDR5 DIMMs and a minimum system memory of 2,048 GB running at 5,200 MT/s in the two-DIMM-per-channel configuration HPE recommends for performance. Scale-out is eight ConnectX-8 adapters supporting InfiniBand XDR or Spectrum-X Ethernet, with storage of eight E1.S drives and two M.2. Power comes from twelve fixed 3,200 W Titanium supplies in an N+N redundant arrangement, and HPE rates the machine at 14.3 kW continuous and 16.4 kW peak. Air cooling a Blackwell Ultra system of this density is unusual and it shows in the mechanicals: the chassis weighs 226 kg, ships pre-racked by default, and HPE requires a server lift on site before its engineers will service it. HPE describes it as delivering 50 percent higher FP4 performance than the prior Blackwell generation but publishes no FLOPS figure of its own, so the compute shown is NVIDIA's specification for the HGX B300 board rather than an HPE claim.
We will point you at suppliers who have it. Free, and no signup.
Systems built on this design
11 configurationsBuilt on the NVIDIA HGX B300 8-GPU baseboard, so accelerator performance matches the reference. Chassis, CPU, memory and cooling are this vendor's own.
System Details
GPU Configuration
System Specifications
Precision Performance Breakdown
| Precision | System Performance | Per GPU | Efficiency |
|---|---|---|---|
| 10 TFLOPS | 1.3 TFLOPS | — | |
| 600 TFLOPS | 75 TFLOPS | — | |
| 9,000 TFLOPS | 1,125 TFLOPS | — | |
| 18,000 TFLOPS | 2,250 TFLOPS | — | |
| 18,000 TFLOPS | 2,250 TFLOPS | — | |
| 36,000 TFLOPS | 4,500 TFLOPS | — | |
| 108,000 TFLOPS | 13,500 TFLOPS | — | |
| FP6 | 36,000 TFLOPS | 4,500 TFLOPS | — |
Where a vendor states a basis, the figure shown is the dense one, and any figure it publishes is listed separately. Vendors commonly headline the sparse number instead: for NVIDIA's 2:4 structured sparsity that is exactly twice the dense figure, though other vendors' sparse modes do not all follow that ratio.
Powered by NVIDIA B300
This system utilizes 8 × NVIDIA B300 SXM 262GB GPUs, each delivering exceptional performance for AI and HPC workloads.
Per GPU TDP
1400W
Per GPU Memory
263 GB
Process Node
4nm
Architecture
Blackwell Ultra
Frequently asked questions
How much does the Compute XD690 cost?
HPE sells the Compute XD690 on quote through OEMs and resellers, and nobody rents a whole one by the hour. Renting its 8 B300 accelerators separately at the cheapest live rate Flopper tracks, $4.99 per GPU-hour across 10 providers, comes to about $39.92 an hour for the equivalent capacity. B300 rental prices →
How much power does the Compute XD690 require?
HPE rates the Compute XD690 at 14.3 kW, which is the figure to plan power delivery and cooling around; per-GPU draw is listed on the accelerator's own page.
How many GPUs are in the Compute XD690?
8. The Compute XD690 carries 8 NVIDIA B300 SXM 262GB accelerators in a rack form factor, and every throughput figure on this page is the total across them. B300 specifications →
Documentation & Resources
Need this system?
Tell us the quantity, timeframe and region. We reply by email with who can supply it.
Flopper Spec Sheet
HPE Compute XD690 specifications, generated from our database. Printable.
Vendor product page
HPE Compute XD690 documentation
HPE Compute XD690 QuickSpecs (a50009220enw, V6)
HPE • 2026-07-06
Typical Use Cases
The HPE Compute XD690 runs 8× B300 GPUs over NVLink 5.0 / NVSwitch 4.0 across the HGX B300 baseboard; 8x NVIDIA ConnectX-8 for InfiniBand XDR or Spectrum-X Ethernet scale-out, delivering 36,000 TFLOPS FP8 dense.