NVIDIA DGX B300
8 × B300 (Blackwell Ultra) per node, with 8 compute rails at 800G. That is 6.4 Tb/s of scale-out network per node.
- GPUs per node8 × B300 (Blackwell Ultra)
- Compute rails8 × 800G
- Scale-out bandwidth6.4 Tb/s
- Storage links2 × 400G
- In-band links2 × 100G
- BMC ports1
- Rack units10U
- Typical power13 kW
- Maximum power14 kW
What this means for the fabric
8 compute NICs means 8 rails. In a rail-optimized design each of those rails is sized on its own against the node count, then multiplied back up, so the leaf tier is driven by the rail count and not by the total endpoint count.
Storage and in-band management are separate fabrics with their own switches and their own optics, and the 1 BMC port per node feed the out-of-band network, which also has to carry every switch and every PDU in the cluster.
Power and racks
At 13 kW typical draw, this node fills a rack's power budget long before it fills the space. A 45 kW rack takes 3 of them on power alone, against 4 on rack units. Power is what actually sets the rack count.
Notes
Blackwell Ultra. Verified: 8 GPUs in 10RU air-cooled, ~14 kW peak, eight OSFP ports serving eight ConnectX-8 VPI adapters at up to 800 Gb/s, plus two dual-port QSFP112 BlueField-3 DPUs. IMPORTANT: ConnectX-8 does 1x800G per port in InfiniBand mode, but in Ethernet mode it runs 2x400G instead — a Spectrum-X build is therefore 16 rails at 400G, not 8 at 800G. This preset models the InfiniBand configuration; set 16 rails at 400G for a Spectrum-X twin-planar design.
Source: NVIDIA DGX B300 product page and technical brief, verified 2026-08. Rack units, GPU count, and network ports confirmed; exact typical draw is approximate. Confirmed 2026-08-06