NVIDIA data center Available

NVIDIA T4

T-Series ยท Turing Architecture

Enquire Now
The NVIDIA T4 is the world's most widely deployed inference accelerator. At just 70W and single-slot form factor (no external power), it fits in virtually any server. Despite its age, it remains the go-to choice for cost-effective AI inference at scale.

Key Features

70W slot-powered Single-slot low-profile INT8 inference Widely supported Cost-effective inference

Full Specifications

Compute

Architecture Turing
Process Node 12nm TSMC
CUDA Cores 2,560
Tensor Cores 320
RT Cores 40
Base Clock 585 MHz
Boost Clock 1590 MHz
FP32 Performance 8.14 TFLOPS
FP16 Performance 65.13 TFLOPS
INT8 Performance 130 TOPS

Memory

Memory Size 16 GB
Memory Type GDDR6
Memory Bus 256-bit
Memory Bandwidth 320 GB/s

Power & Physical

TDP 70W
Form Factor PCIe
Slot Width 1-slot
Card Length 169 mm
Power Connectors PCIe slot powered

Features & Connectivity

PCIe Version PCIe 3.0 x16
NVLink Support No
Multi-GPU Support No

Availability

MSRP (USD) $2,500
Release Date Mar 2019
Status Available

Industries

Cloud Computing AI/ML Healthcare Retail

Use Cases

AI Inference Video Transcoding Virtual Desktop Edge Inference

Interested in the NVIDIA T4?

Get pricing, availability, and bulk discount information from our team.

Enquire Now

Related GPUs

NVIDIA data center

NVIDIA H100 SXM

Memory

80GB HBM3

FP32

66.91 TFLOPS

TDP

700W

FP16

989.4 TFLOPS

Available View Specs
NVIDIA data center

NVIDIA H100 PCIe

Memory

80GB HBM3

FP32

51.22 TFLOPS

TDP

350W

FP16

756 TFLOPS

Available View Specs
NVIDIA data center

NVIDIA H200 SXM

Memory

141GB HBM3e

FP32

66.91 TFLOPS

TDP

700W

FP16

989.4 TFLOPS

Available View Specs
NVIDIA data center

NVIDIA B200

Memory

192GB HBM3e

FP32

90 TFLOPS

TDP

1000W

FP16

1800 TFLOPS

Available View Specs