NVIDIA HGX B300

Name: NVIDIA HGX B300
Brand: NVIDIA
Price: Contact Sales
Availability: InStock

The NVIDIA HGX B300, powered by NVIDIA Blackwell Ultra, is a premier accelerator designed to handle demanding AI and high-performance computing workloads.

Contact sales

View pricing

Accelerated performance for AI inference

7.5

X

MORE COMPUTE*

7.5

X

MORE COMPUTE*

Fifth-generation NVIDIA Tensor Cores with theNVFP4 precision format deliver 15 petaFLOPS of dense compute per GPU, a 7.5X increase over an NVIDIA H100 Tensor Core GPU, for low-latency, large-scale LLM and reasoning inference.

50

x

HIGHER THROUGHPUT
PER MEGAWATT*

50

x

HIGHER THROUGHPUT
PER MEGAWATT*

Blackwell Ultra systems deliver up to 50X higher throughput per megawatt than an NVIDIA H100 Tensor Core GPU for low-latency agentic workloads, through hardware-software codesign.

35

x

LOWER COST
PER TOKEN*

35

x

LOWER COST
PER TOKEN*

Up to 35X lower cost per token than an NVIDIA H100 Tensor Core GPU for real-time reasoning and agentic AI, redefining the economics of AI inference.

*Compared to NVIDIA H100 TENSOR CORE GPU

Ideal workloads for the NVIDIA HGX B300

High-throughput inference for reasoning models

Serve demanding generative and reasoning models in production. Added memory capacity and bandwidth over B200 give real headroom for larger models, longer context, and the higher token volumes reasoning workloads generate, at a flexible single-system scale.

Generative AI development and fine-tuning

Train and fine-tune advanced generative AI models and LLMs, including mixture-of-experts (MoE) models, on a scale-up 8-GPU platform. The B300’s larger HBM and second-generation Transformer Engine take on bigger models and longer context than the B200 generation.

Pre-training and Post Training

A versatile accelerated platform for AI, from real-time recommendations to analytics and complex decision systems, alongside compute-intensive HPC and scientific simulation.

Build the future faster with Crusoe Cloud

Up to 20 times faster and 81% less expensive than traditional cloud providers.

Unparalleled performance

Scale ambitiously and fearlessly knowing your AI workloads are backed by peerless infrastructure.

Accelerated breakthroughs

Focus on innovation not infrastructure with intuitive, AI-native systems designed to keep you building.

Abundant compute

Achieve your AI potential with vast compute and energy resources.

Crusoe provides the latest NVIDIA hardware, extraordinary support, and overall a great partner to enable our data, training, and inference infrastructure. Crusoe is consistently accommodating to our needs and is not afraid to dive deep in helping us solve hard problems.

Philip Petrakian

Member of Technical Staff

This was not tens of nodes or hundreds of nodes, but thousands of nodes on extremely short notice. I remember being on the call with Crusoe late evening Friday night, Saturday morning, trying to figure out the best way to get this capacity. We were able to strike a deal within a couple of days, and we got those nodes up and running within a few hours of signing.

Chenyu Zhao

Co-Founder

There are a lot of providers selling GPUs out there, but ultimately the GPU is most useful when it's backed by reliable infrastructure. We've had good success with Crusoe: the network fabric is very performant, and we're able to pump a lot of gigabits on a constant basis.

Sachin Agarwal

ML Infrastructure & Security Engineering Lead

We benchmarked the cluster, and we realized that Crusoe matches the state-of-the-art speed in terms of both the GPUs and the storage. We decided to go with Crusoe because it was the best possible choice.

David Novotný

Co-Founder + CTO

NVIDIA HGX B300

Accelerated performance for AI inference

Ideal workloads for the NVIDIA HGX B300