HPE ProLiant Compute XD685 (HGX B300)
The eight-way XD685 in its NVIDIA HGX B300 configuration, which requires the high-power liquid-cooled chassis S6Y07A rather than the standard DLC one. This is the denser sibling of the air-cooled XD690, which reaches the same eight Blackwell Ultra GPUs in 10U where this does it in 5U. Two fifth-generation AMD EPYC processors, 24 DIMM slots and up to 6 TB of DDR5-6400, eight EDSFF NVMe E3.S drives. HPE publishes no system power draw for the XD685, only twelve 3,000 W Titanium supplies with ten deployable, so unlike the XD690 no figure is recorded; the compute shown is NVIDIA's specification for the HGX B300 baseboard 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 ProLiant Compute XD685 (HGX B300) cost?
HPE sells the ProLiant Compute XD685 (HGX B300) 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 ProLiant Compute XD685 (HGX B300) require?
HPE has not published a power figure for the ProLiant Compute XD685 (HGX B300), and Flopper does not derive one from the accelerator count because the rest of the system draws power too.
How many GPUs are in the ProLiant Compute XD685 (HGX B300)?
8. The ProLiant Compute XD685 (HGX B300) 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 ProLiant Compute XD685 (HGX B300) specifications, generated from our database. Printable.
Vendor product page
HPE ProLiant Compute XD685 (HGX B300) documentation
HPE Compute XD690 QuickSpecs (a50009220enw, V6)
HPE • 2026-07-06
Typical Use Cases
The HPE ProLiant Compute XD685 (HGX B300) runs 8× B300 GPUs over NVLink 5.0 / NVSwitch 4.0 across the HGX B300 baseboard; 4x FHHL PCIe Gen5 x16 slots for fabric, NIC or DPU, delivering 36,000 TFLOPS FP8 dense.