(All-cores)
(Single-core)
Specifications
Server Metadata
Vendor ID | aws |
Name | p6-b200.48xlarge |
Description | GPU accelerated Gen6 48xlarge |
Family | p6-b200 |
Hw Virt | - |
Status | active |
Observed At | 2026-10-26T10:39:47.768384 |
Availability
| REGION / ID | SPOT | ONDEMAND |
|---|---|---|
Oregon (US) / us-west-2 | 64.926367 USD/h | 113.9328 USD/h |
Ohio (US) / us-east-2 | 78.744467 USD/h | 113.9328 USD/h |
Northern Virgina (US) / us-east-1 | 83.8037 USD/h | 113.9328 USD/h |
Stockholm (SE) / eu-north-1 | 16.1205 USD/h | 143.242 USD/h |
Mumbai (IN) / ap-south-1 | 54.46125 USD/h | 160.6453 USD/h |
Hyderabad (IN) / ap-south-2 | 16.065 USD/h | 160.65 USD/h |
Paris (FR) / eu-west-3 | 50.2703 USD/h | 174.3172 USD/h |
Processor
vCPUs | 192 |
Hypervisor | nitro |
CPU Allocation | Dedicated |
CPU Cores | 96 |
CPU Speed | 2.4 GHz |
CPU Architecture | x86_64 |
CPU Manufacturer | Intel |
System Resources and Accelerators
| MEMORY | |
|---|---|
Memory Amount | 2 TB |
| ACCELERATORS | |
|---|---|
Accelerator Count | 8 |
Accelerator Memory Min | 179 GiB |
Accelerator Memory Total | 1 TB |
Accelerator Type | GPU |
Accelerator Manufacturer | NVIDIA |
Accelerator Family | Blackwell |
Accelerator Model | B200 |
Accelerators |
|
| STORAGE | |
|---|---|
Storage Size | 30400 GB |
Storage Type | nvme ssd |
Storages |
|
| NETWORK | |
|---|---|
Network Speed Baseline | 200 Gbps |
Network Speed Max | 200 Gbps |
Network Storage Speed Baseline | 100 Gbps |
Network Storage Speed Max | 100 Gbps |
Inbound Traffic | 0 GB/month |
Outbound Traffic | 0 GB/month |
IPv4 | 0 |
Server Description
A high-density GPU instance featuring eight Blackwell accelerators, massive NVMe storage, and high-bandwidth networking for parallel computing workloads.
Amazon Web Services p6-b200.48xlarge is a GPU-accelerated server instance built on the Nitro hypervisor. It features 192 dedicated x86_64 vCPUs from Intel running at 2.4 GHz, alongside 2048.0 GB of system memory. The hardware configuration is distinguished by eight NVIDIA Blackwell B200 GPUs providing 1432 GB of total VRAM, paired with 30400 GB of local NVMe SSD storage. Network performance is anchored by a baseline bandwidth of 200 Gbps. This high-density resource profile is designed for intensive parallel computing tasks, including large-scale machine learning model training, deep learning inference, and massive data science workloads. The instance trades a premium hardware class cost structure for extreme computational density and high-speed local storage access.
Economics
Alternatives
Servers of the Same Family
| INSTANCE | vCPUs | MEMORY | Accelerators |
|---|
Similar Servers
| INSTANCE | VENDOR | vCPUs | MEMORY | Accelerators |
|---|