The P4d instance family, generally available since November 2, 2020, features Intel Cascade Lake processors and NVIDIA A100 Tensor Core GPUs. These accelerated computing instances are designed for machine learning training and high-performance computing, offering 400 Gbps networking. Each P4d instance includes 8 TB of NVMe-based SSD storage for fast access to large datasets. They are available in the p4d.24xlarge size, providing 96 vCPUs.

Source

Info #

Instance Types

p4d.24xlarge

vCPUs

Up to 96

Memory

Up to 1152 GiB

Architecture

x86_64

Processor

Intel

GPUs

Up to 8

Performance ranking #

Ranked by CPU performance (Passmark)

m8a, r8a

3846

c7i, c7i-flex, c8i, c8i-flex, i7i, i7ie, m7i, m7i-flex, m8i, m8i-flex, r7i, r7iz, r8i, r8i-flex, u7i-12tb, u7i-6tb, u7i-8tb, u7in-16tb, u7in-24tb, u7in-32tb

3005

c7a, m7a, r7a

2885

c6a, m5zn, m6a, r6a

2593

c6i, c6id, c6in, i4i, m6i, m6id, m6idn, m6in, r6i, r6id, r6idn, r6in, z1d

2297

c5, c5a, c5ad, c5d, c5n, c8g, c8gd, c8gn, i8g, i8ge, m5d, m8g, m8gd, r8g, r8gb, r8gd, r8gn, x8g

1896

c4, m5dn, r5dn, r5n, t2

1777

c3, c7g, c7gd, c7gn, i3, i3en, m4, m5, m5n, m7g, m7gd, r3, r4, r5, r5b, r5d, r7g, r7gd, t3

1625

m5a, m5ad, r5a, r5ad, t3a

1419

#10

c6g, c6gd, c6gn, i4g, m6g, m6gd, r6g, r6gd, t4g

1097

#11

a1, c1, d2, d3, d3en, dl1, f1, f2, g4ad, g4dn, g5, g5g, g6, g6e, g6f, gr6, gr6f, h1, hpc7g, i2, im4gn, inf1, inf2, is4gen, m1, m2, m3, mac-m4, mac-m4pro, mac1, mac2, mac2-m1ultra, mac2-m2, mac2-m2pro, p3, p3dn, p4d, p4de, p5, p5en, p6-b200, t1, trn1, trn1n, u-3tb1, u-6tb1, vt1, x1, x1e, x2gd, x2idn, x2iedn, x2iezn

Unknown

Available Regions #

🇯🇵 ap-northeast-1

🇰🇷 ap-northeast-2

🇮🇳 ap-south-1

🇸🇬 ap-southeast-1

🇦🇺 ap-southeast-2

🇨🇦 ca-central-1

🇩🇪 eu-central-1

🇸🇪 eu-north-1

🇮🇪 eu-west-1

🇬🇧 eu-west-2

🇧🇷 sa-east-1

🇺🇸 us-east-1

🇺🇸 us-east-2

🇺🇸 us-west-2

Pricing Charts #

Platform:

p4d.24xlarge 96 vCPU, 1152 GiB

On-Demand Price

Spot Price

Markdown (.md) | JSON (.json)

Home

RunsOn