Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.coreweave.com/llms.txt

Use this file to discover all available pages before exploring further.

Powered by eight NVIDIA RTX Pro 6000 GPUs based on the Blackwell architecture, these instances provide a versatile and efficient solution for a mix of AI and professional graphics workloads. Each GPU has 96 GB of GDDR7 memory and connects via a high-speed PCIe interface. While they lack NVLink for memory pooling across GPUs, their large individual GPU memory makes them excellent for running multiple inference jobs in parallel or handling high-resolution rendering tasks.

​
Specifications

FeatureDetail
CategoryProfessional AI & Graphics
Instance IDrtxp6000-8x
GPU8x NVIDIA RTX Pro 6000
GPU RAM96 GB
GPU ConnectivityPCIe
CPU ModelIntel Emerald Rapids 8562Y+ (2.80 GHz)
vCPUs128
RAM1024 GB
Local Storage7.68 TB
Network SpeedDual-port 100GbE
AvailabilityEU-SOUTH-04A
US-CENTRAL-06A
US-EAST-01A
US-EAST-04A
US-EAST-06A
US-EAST-13A
US-EAST-14A
US-WEST-04A
US-WEST-09B

​
Primary use cases

High-performance inference and fine-tuning for mid-sized models and high-fidelity rendering. Inference and fine-tuning of mid-sized models up to 70B, such as Gemma 4 31B and Qwen 3.6 35B-A3B, on a per-GPU basis.
Last modified on May 12, 2026