NVIDIA Tesla T4: GPU Specs & Benchmarks
The Tesla T4 is a graphics card by NVIDIA, built on the 12 nm process and based on the TU104 graphics processor (GPU). The video card specifications and performance tests (benchmarks) are listed below.
Recommended Gaming Resolutions 640x480 1280x720 1366x768 1600x900 1920x1080 2560x1440 3840x2160
Benchmarks
- PassMark G3D
- 11257
- PassMark G2D
- 573
- 3DMark Time Spy
- 4988
- 3DMark Time Spy Extreme
- 2451
- 3DMark Fire Strike Extreme
- 7046
Graphics Processor (GPU)
- GPU Name
- TU104
- Model number
- TU104-895-A1
- Architecture
- Turing
- Foundry
- TSMC
- Process Size
- 12 nm
- Transistors
- 13,600 million
- Die Size
- 545 mm²
Graphics Card
- Release Date
- Sep 13th, 2018
- Family
- Tesla
(Txx) - Production
- Active
- Bus Interface
- PCIe 3.0 x16
Memory
- Memory Size
- 16 GB
- Memory Type
- GDDR6
- Memory Bus
- 256 bit
- Bandwidth
- 320.0 GB/s
Performance
- Pixel fillrate
- 101.8 GPixel/s
- Texture fillrate
- 254.4 GTexel/s
- FP16 (half) performance
- 65.13 TFLOPS (8:1)
- FP32 (float) performance
- 8.141 TFLOPS
- FP64 (double) performance
- 254.4 GFLOPS (1:32)
Clock Speeds
- Base Clock
- 585 MHz
- Boost Clock
- 1590 MHz
- Memory Clock
- 1250 MHz
10 Gbps effective
Render Config
- Shading Units
- 2560
- TMUs
- 160
- ROPs
- 64
- RT Cores
- 40
- L1 Cache
- 64 KB (per SM)
- L2 Cache
- 4 MB
- SM Count
- 40
- Tensor Cores
- 320
Board Design
- Slot Width
- Single-slot
- Length
- 168 mm
6.6 inches - Thermal design power (TDP)
- 70 W
- Suggested PSU
- 250 W
- Display Connectors
- No outputs
- Power Connectors
- None
- Board Number
- PG183 SKU 200
API support
- DirectX
- 12 Ultimate (12_2)
- OpenGL
- 4.6
- OpenCL
- 3.0
- Vulkan
- 1.2
- Shader Model
- 6.6
- CUDA
- 7.5
