AWS G3 instance types

G3 is a gpu & accelerated Amazon EC2 family with 3 instance types, from 16 – 64 vCPUs and 122 GiB – 488 GiB of memory with NVIDIA M60 accelerators, running on Intel Xeon E5-2686 v4 (Broadwell). Linux on demand starts at $1.14 per hour.

gpu & acceleratedx86-64

sizes: 3
vCPUs: 16 – 64
memory: 122 GiB – 488 GiB
accelerator: M60
on-demand from: $1.14

Compare sizes

G3 sizes and prices

Linux, hourly, US East (N. Virginia) (other regions on each size's page)

Size	vCPU	Memory	Accelerator	Local storage	On-demand	Monthly	Spot
g3.4xlarge	16	122 GiB	1 × NVIDIA M60	–	$1.14	$832	$0.4706
g3.8xlarge	32	244 GiB	2 × NVIDIA M60	–	$2.28	$1,664	$0.9581
g3.16xlarge	64	488 GiB	4 × NVIDIA M60	–	$4.56	$3,329	$1.869

Other gpu & accelerated families on AWS

Dl1 1 Dl2q 1 F1 3 F2 3 G3s 1 G4ad 5 G4dn 7 G5 8 G5g 6 G6 8 G6e 8 G6f 4 G7 6 G7e 6 Gr6 2 Gr6f 1 Inf1 4 Inf2 4 P2 3 P3 3 P3dn 1 P4d 1 P4de 1 P5 2 P5e 1 P5en 1 P6-b200 1 P6-b300 1 Trn1 2 Trn1n 1

G3 FAQ

What sizes does the AWS G3 family have?

G3 has 3 instance types, from g3.4xlarge (16 vCPU, 122 GiB) to g3.16xlarge (64 vCPU, 488 GiB). They run on Intel Xeon E5-2686 v4 (Broadwell).

What is the cheapest G3 instance type?

g3.4xlarge at $1.14 per hour (Linux, on demand) in US East (N. Virginia), about $832 per month.

What is G3 best for?

G3 is a gpu & accelerated family. GPUs and AI accelerators for training, inference, rendering and video.