Skip to main content

RTX5090 vs T4

The RTX5090 delivers 3.2× the FP16 compute of the T4 while costing 1.9× more on average, making it 70% more cost-efficient per TFLOP.

Spec Comparison

Spec
RTX5090
T4
Architecture
Blackwell
Older
VRAM
32 GB
16 GB
FP16 TFLOPS
210
65
Memory Bandwidth
1,792 GB/s
320 GB/s
MSRP
$1,999
N/A
Used/Market Price
N/A
$1,500

Live Pricing

RTX5090
Cheapest
$0.213/hr
Median
$1.73/hr
Average
$2.23/hr
Providers
3
Instances
108
T4
Cheapest
$0.0684/hr
Median
$0.909/hr
Average
$1.53/hr
Providers
8
Instances
1557

Cost Efficiency

Metric
RTX5090
T4
$/TFLOP/hr
$0.0082
$0.0140
$/GB-VRAM/hr
$0.0540
$0.0568

Lower $/TFLOP and $/GB-VRAM is better. Based on median hourly pricing.

Provider Availability

RTX5090 Cloud Pricing

108 instances
ProviderGPUsVRAMRegionTypePrice/hr
CHEAPESTVast.ai1x32 GBChinaSpot$0.213Rent
Vast.ai1x32 GBChinaOn-Demand$0.236Rent
Vast.ai1x32 GBEU-CentralSpot$0.267Rent
Vast.ai1x32 GBUS-CentralSpot$0.268Rent
Vast.ai1x32 GBUS-CentralOn-Demand$0.278Rent
Vast.ai1x32 GBChinaSpot$0.289Rent
Vast.ai1x32 GBEU-CentralSpot$0.333Rent
Vast.ai1x32 GBChinaOn-Demand$0.401Rent
Vast.ai2x64 GBmx-mexicoSpot$0.453Rent
RunPod1x32 GBEU-RO-1Spot$0.530Rent

T4 Cloud Pricing

1557 instances
ProviderGPUsVRAMRegionTypePrice/hr
CHEAPESTAzure1x16 GBAsia-PacificSpot$0.0684Rent
Azure1x16 GBUS-CentralSpot$0.0686Rent
Azure1x16 GBAsia-PacificSpot$0.0977Rent
Azure1x16 GBUS-CentralSpot$0.0980Rent
GCP1x16 GBme-west1-bSpot$0.112Rent
GCP1x16 GBme-west1-cSpot$0.112Rent
GCP1x16 GBEU-WestSpot$0.117Rent
GCP1x16 GBme-west1-bSpot$0.118Rent
GCP1x16 GBme-west1-cSpot$0.118Rent
AWS1x16 GBSouth AmericaSpot$0.123Rent

Compare with Other GPUs

RTX5090 vs ...

T4 vs ...

We use cookies for analytics and to remember your preferences. Privacy Policy