Cisco UCS C880A M8 (HGX B300)
8 × B300 (Blackwell Ultra) SXM 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) SXM
- 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 on the HGX platform. Verified: 8 x HGX B300 SXM, two 6th Gen Intel Xeon, one ConnectX-8 SuperNIC per GPU, air-cooled. Rack units and power are working figures — confirm both, since power drives rack count directly at this draw.
Source: Cisco UCS C880A M8 data sheet, verified 2026-08. GPU count, generation, and per-GPU networking confirmed; rack units and power are estimates. Needs verification 2026-08-06