The T4 is a high-performance datacenter GPU. Featuring 16GB of ultra-fast memory, it is engineered for the most demanding AI model training, large language models (LLMs), and complex scientific computing.
Recommended Scenarios
Deep Learning
Model Inference
Video Encoding
Architecture
Turing
VRAM Capacity
16GB
Bandwidth
320 GB/s
CUDA Cores
2560
FP16 Perf.
65 TFLOPS
Power (TDP)
70W