Aircloud Compute is now Lightyard. Aircloud continues as a private inference platformAircloud continues for inference

Hardware · HGX

NVIDIA HGX B300

An eight-GPU Blackwell Ultra system that runs on air. We design, build and operate clusters of them.

Sheet 01 · HGX B3008 GPUs per node
GPUs
8 × B300
GPU memory
288 GB HBM3e each
Network
800 Gb/s per GPU
Power
About 14 kW per system
Lead time
About 10 to 14 weeks from signing
Drawing is illustrative · Figures are NVIDIA's
Specifications

NVIDIA HGX B300 specifications.

What each eight-GPU system brings, and what it asks for.

Generation
Blackwell Ultra
GPUs
8 GPUs per nodeLinked by NVLink inside the system.
GPU memory
288 GB HBM3e per GPU, 2.3 TB per system
NVLink
14.4 TB/s across 8 GPUsInside the system. Between systems, the scale-out fabric carries the traffic.
Scale-out network
800 Gb/s per GPU (ConnectX-8)One NIC per GPU, so the fabric is sized per GPU rather than per system.
Power
About 14 kW per systemNVIDIA's figure for its eight-GPU B300 system.
Cooling
AirLiquid-cooled versions exist for halls with facility water.
Air-cooled rack
4 systems, about 56 kWNVIDIA's reference layout. Your hall may call for fewer per rack.
Reference designs
32, 64 and 128 nodesPod sizes in NVIDIA's reference architecture for HGX B300.
Lead time
About 10 to 14 weeks from signing

HGX B300 figures are NVIDIA's published specifications for its eight-GPU system.

Site requirements

What a rack of them asks of the hall.

An air-cooled rack, front elevation. Each note matches a number on the drawing.

  1. 1

    Two power feeds per rack

    Each system draws about 14 kW per system, fed from A and B power strips on separate circuits, so one feed can fail without taking the rack down.

  2. 2

    Air in at the front, out at the back

    Cold aisle in through the fan wall, hot air out the back into a contained hot aisle. At this density the hall needs hot-aisle containment.

  3. 3

    800 Gb/s per GPU to the leaf switches

    8 ConnectX-8 links per system, one per GPU, run to leaf switches in a network rack nearby. Storage and management networks run alongside.

  4. 4

    4 systems to a rack, about 56 kW

    That's NVIDIA's air-cooled layout. Where a position can't feed it, the same systems spread across more racks.

Choosing a platform

HGX B300 or GB300 NVL72?

The same GPU generation in a different unit. The choice usually comes down to how large your models are and what the site can take.

HGX B300 or GB300 NVL72?
GB300 NVL72HGX B300
Unit72 GPUs per rack8 GPUs per node
NVLink domain72 GPUs in one rack8 GPUs in one system
PowerUp to 142 kW per rackAbout 14 kW per system
CoolingLiquid, at the rackAir, or liquid where the hall has it
Smallest clusterOne rack (72 GPUs)8 nodes (64 GPUs)
Fits bestModels split across many GPUs, on sites built for liquid coolingModels that fit in eight GPUs, and halls without facility water

Both are quoted per project. We recommend one once we know the workload and the site.

Other platforms

Other NVIDIA platforms we build on.

The same four stages on each: design, source, build and operate. All hardware.

Questions

HGX B300 questions.

We build HGX B300 clusters as a deployment your team runs, a managed cluster you own and we operate, or a reserved cluster we own. Other platforms.

Get started

Tell us where you're starting.

Capital, hardware, a site or a team: tell us what you have and when you need it running. We usually reply within a few hours and come back with a written plan.

sales@lightyard.ai