B300 (InfiniBand) - CoreWeave Docs

Powered by eight NVIDIA B300 Blackwell GPUs, these instances deliver outstanding performance for enterprise AI workloads, including training and real-time inference. Compared to B200 systems, they offer more performance per GPU, 50% greater GPU memory, and double the InfiniBand speed with 800G XDR non-blocking NVIDIA Quantum-2 fabric.

Specifications

Feature	Detail
Category	State-of-the-Art Compute
Instance ID	`b300-8x`
GPU	8x NVIDIA B300
GPU RAM	270 GB
GPU Connectivity	Quantum-X800 InfiniBand & NVLink
CPU Model	2 x Intel Granite Rapids (6747P) (2.70 GHz)
vCPUs	192
RAM	4096 GB
Local Storage	61.44 TB
Network Speed	Dual-port 200GbE
Default GPU driver	`580`
Compatible GPU driver	`580`, `595`
Availability	US-CENTRAL-06A US-EAST-13A US-WEST-01A US-WEST-10A

Primary use cases

Training foundation models from scratch (130B+ parameters), massive-scale inference, and developing frontier AI systems.

Recommended models

DeepSeek V4 Pro, Kimi K2.6, GLM 5.1, and other future advanced GPT-5 class models, complex Mixture-of-Experts (MoE) models, and large multimodal systems built for coding and agentic workflows.

​Specifications

​Primary use cases

​Recommended models

Specifications

Primary use cases

Recommended models