NVIDIA T4 16GB
Turing PCIe 2019 12nm
FP32
8.1
TFLOPS
VRAM
16 GB
GDDR6
TDP
70 W
115.7 TFLOPS/kW
Bandwidth
300 GB/s
memory
Performance Metrics
Peak theoretical throughput by precision type
| Precision | Peak TFLOPS | Efficiency |
|---|---|---|
| INT8 | 130.0 | 1.857 TFLOPS/W |
| INT4 | 260.0 | 3.714 TFLOPS/W |
| FP16 | 65.0 | 0.929 TFLOPS/W |
| FP32 | 8.1 | 0.116 TFLOPS/W |
FP16 Efficiency
0.929 TFLOPS/W
65.0 TFLOPS / 70W
FP32 Efficiency
0.116 TFLOPS/W
8.1 TFLOPS / 70W
Power Specifications
TDP
70 W
Max Power
81 W
Power Connector
PCIe Slot
Cooling
Air
Memory Specifications
Capacity
16 GB
Type
GDDR6
Bandwidth
300 GB/s
Interface
--
Hardware & Design
Form Factor
PCIe
Architecture
Turing
Process Node
12nm
Launch Year
2019
Variant
16GB
Market Segment
Professional
Common Use Cases
AI Inference Video Processing Edge Computing Computer Vision
The NVIDIA T4 is optimized for high-performance computing tasks with Turing architecture delivering 8.1 TFLOPS of compute power.
Where to Rent
Compare cloud providers offering on-demand GPU instances for AI training, inference, and HPC workloads.
Browse GPU Cloud ProvidersStay Updated on GPU Releases
Get notified when new GPUs are added or specifications are updated.
Loading verification...
No spam, unsubscribe anytime.