A consumer GPU against a data center card, one Ampere and one Volta: 24 GB GDDR6X against 32 GB HBM2, 13% more memory bandwidth on the V100S, and NVLink 300 GB/s on the V100S where the RTX 3090 Ti is PCIe only.

At a glance

Updated 7 minutes ago
Memory
24 GB
GDDR6X
Memory bandwidth
1.01 TB/s
From
$0.28 /GPU/hr
2 providers
Memory
32 GB
HBM2
Memory bandwidth
1.13 TB/s
From
$0.88 /GPU/hr
1 provider

Price comparison

Cheapest listed price per GPU per hour by billing type, and the median across providers.

Billing RTX 3090 Ti V100S Difference
On-demand $0.28 $0.88 3.1x more expensive on V100S
Spot $0.10 No spot listings
Median $0.28 $0.88 3.1x more expensive on V100S

Median: Median across providers, one vote each, so a large catalog does not outweigh a small one.

Price history

RTX 3090 Ti vs V100S price history

Weekly median on-demand price per GPU per hour

Last 12 months
Aggregating historical prices...

Specs comparison

Spec RTX 3090 Ti V100S Difference
Memory
Capacity 24 GB GDDR6X 32 GB HBM2 1.3x more on V100S
Bandwidth 1,008 GB/s 1,134 GB/s 1.1x higher on V100S
Bus width 384-bit 4,096-bit 11x wider on V100S
Compute · dense
FP16 / BF16 80 TFLOPS 130 TFLOPS 1.6x higher on V100S
INT8 320 TOPS
FP32 40 TFLOPS 16.4 TFLOPS 2.4x higher on RTX 3090 Ti
FP64 Not supported 8.2 TFLOPS V100S only
Platform
Interconnect PCIe only NVLink 300 GB/s NVLink on V100S only
Board power 450 W 250 W 1.8x higher on RTX 3090 Ti
Released Q1 2022 Q4 2019 2 years newer on RTX 3090 Ti
Precision
Supported formats FP16BF16TF32FP32INT4INT8 FP16FP32FP64INT8

Compute: Vendor peak figures, dense and per GPU. Not measured throughput.

Source: RTX 3090 Ti datasheet and V100S datasheet.

Where to rent them

Providers listing these GPUs, those with both first, so you can switch without moving clouds.

Provider RTX 3090 Ti /GPU/hr V100S /GPU/hr
Salad logo Salad On-Demand $0.28 --
Runpod logo Runpod On-Demand $0.27 --
OVHcloud logo OVH -- On-Demand $0.88

Similar GPUs

Other comparisons in the same class.

Our data for Nvidia RTX 3090 Ti was last updated on Sept. 7, 2026, and for Nvidia V100S on Sept. 7, 2026.