Hot starts, batch inference, and what's next for Runpod Serverless. Webinar June 25.

GPU Models

Discover the right GPU for your workloads

Browse GPU models across 30+ regions and find detailed specs, pricing, and availability with thousands of instances ready to deploy.

GPU

>80GB VRAM

B300

288 GB HBM3e
251 GB RAM
32
vCPUs
$7.39/hr
B300

H200

141 GB VRAM
276 GB RAM
24
vCPUs
$3.59/hr
H200

B200

180 GB VRAM
283 GB RAM
28
vCPUs
$5.89/hr
B200

RTX Pro 6000

96 GB VRAM
188 GB RAM
16
vCPUs
$1.69/hr
RTX Pro 6000

H100 NVL

94 GB VRAM
94 GB RAM
16
vCPUs
$2.59/hr
H100 NVL
80GB VRAM

H100 PCIe

80 GB VRAM
188 GB RAM
16
vCPUs
$1.99/hr
H100 PCIe

H100 SXM

80 GB VRAM
125 GB RAM
20
vCPUs
$2.69/hr
H100 SXM

A100 PCIe

80 GB VRAM
117 GB RAM
8
vCPUs
$1.19/hr
A100 PCIe

A100 SXM

80 GB VRAM
125 GB RAM
16
vCPUs
$1.39/hr
A100 SXM
48GB VRAM

L40S

48 GB VRAM
94 GB RAM
16
vCPUs
$0.79/hr
L40S

RTX 6000 Ada

48 GB VRAM
167 GB RAM
10
vCPUs
$0.74/hr
RTX 6000 Ada

A40

48 GB VRAM
50 GB RAM
9
vCPUs
$0.35/hr
A40

L40

48 GB VRAM
94 GB RAM
8
vCPUs
$0.69/hr
L40

RTX A6000

48 GB VRAM
50 GB RAM
9
vCPUs
$0.33/hr
RTX A6000
32GB VRAM

RTX 5090

32 GB VRAM
35 GB RAM
9
vCPUs
$0.69/hr
RTX 5090
24GB VRAM

L4

24 GB VRAM
50 GB RAM
12
vCPUs
$0.44/hr
L4

RTX 3090

24 GB VRAM
125 GB RAM
16
vCPUs
$0.22/hr
RTX 3090

RTX 4090

24 GB VRAM
41 GB RAM
6
vCPUs
$0.34/hr
RTX 4090

RTX A5000

24 GB VRAM
25 GB RAM
9
vCPUs
$0.16/hr
RTX A5000
16GB VRAM

RTX 2000 Ada

16 GB VRAM
31 GB RAM
6
vCPUs
$0.5/hr
RTX 2000 Ada
Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.

Build what’s next.

Build, train, and scale AI workloads on Runpod with cloud GPUs, Serverless, and Clusters.