Penguin Solutions Relion XE4418GTS-DTC vs QCT QuantaGrid D75H-10U

Both are built on the NVIDIA HGX B300 8-GPU baseboard, so their accelerator performance is identical rather than merely similar. The choice between them is chassis, cooling, expansion and supplier, not FLOPS.

What actually differs

SpecificationPenguin Solutions Relion XE4418GTS-DTCQCT QuantaGrid D75H-10U
VendorPenguin SolutionsQCT
Part numberRelion XE4418GTS-DTCD75H-10U
Form factorrackrack
Released
Accelerator8x B3008x B300
Aggregate memory
Aggregate bandwidth
System power
InterconnectPenguin publishes no interconnect figure; expansion is 4x PCIe Gen5 x16 FHHL double-widthOne NVIDIA HGX B300 8-GPU baseboard; scale-out is eight ConnectX-8 OSFP ports carrying 800G Ethernet or InfiniBand at one port per GPU for GPU-Direct RDMA

Rows shown in grey are identical between the two.

Penguin Solutions Relion XE4418GTS-DTC

The Penguin Solutions Relion XE4418GTS-DTC is a 4U GPU server carrying eight NVIDIA HGX B300 SXM6 modules of 288 GB each, hosted by Intel Xeon 6 (6700/6500 Series) processors with 4x PCIe Gen5 x16 FHHL double-width. Direct-to-chip liquid cooling puts a full Blackwell Ultra baseboard in 4U, half the height of Penguin's air-cooled B300 machine. Penguin publishes only rack height, host processor, expansion slots and the accelerator for its servers, so no power draw, total memory, interconnect bandwidth or throughput figure is shown here; its full datasheets are hosted off its own domain and were not used as a source.

Vendor product page

QCT QuantaGrid D75H-10U

QCT's 10U Blackwell Ultra server, built on the NVIDIA HGX B300 platform with two Intel Xeon 6 processors. Networking is eight ConnectX-8 OSFP ports at 800G, one per accelerator, for one-to-one GPU-Direct RDMA, and there is room for four full-height full-length PCIe Gen 5 slots. QCT quotes 72 PFLOPS of FP8 and 144 PFLOPS of FP4 without saying whether either is dense or sparse. Both match NVIDIA's sparse figures for this baseboard exactly, and neither matches the dense figures of 36 and 108, so they are recorded as sparse. Worth noting QCT calls the FP8 number a training figure, which would normally imply dense; the number itself settles the basis, not the label. Power is twelve 3,200 W supplies in N+N redundancy, which is capacity rather than draw, so no system power is shown.

Vendor product page