GPU Comparison
GEFORCE
NVIDIA CMP 30HX
CORE STATE
TU116
VRAM
6 GB
CLOCK SPEED
1785 MHz
TDP
125 W
BUS WIDTH
192 bit
ARCHITECTURE
Turing
PROCESS
12 nm
LAUNCH DATE
2021
VS
GEFORCE
Tesla T4
CORE STATE
TU104
VRAM
16 GB
CLOCK SPEED
1590 MHz
TDP
70 W
BUS WIDTH
256 bit
ARCHITECTURE
Turing
PROCESS
12 nm
LAUNCH DATE
2018
PERFORMANCE BENCHMARKS
geekbench_opencl
geekbench_vulkan
DETAILED SPECIFICATIONS
SPECIFICATION
CMP 30HX
Tesla T4
Core Specs
Shading Units
1,408
2,560
+81.8%
Shaders
1,408
2,560
+81.8%
TMUs
88
160
+81.8%
ROPs
48
64
+33.3%
SM Count
22
40
+81.8%
Clocks
Base Clock
1530 MHz
585 MHz
Boost Clock
1785 MHz
1590 MHz
Memory Clock
1750 MHz
14 Gbps effective
1250 MHz
10 Gbps effective
Memory
Memory Size
6 GB
16 GB
VRAM (MB)
6,144
16,384
+166.7%
Memory Type
GDDR6
GDDR6
Memory Bus
192 bit
256 bit
Bandwidth
336.0 GB/s
320.0 GB/s
Cache
L1 Cache
64 KB (per SM)
64 KB (per SM)
L2 Cache
1536 KB
4 MB
Performance
Pixel Rate
85.68 GPixel/s
101.8 GPixel/s
Texture Rate
157.1 GTexel/s
254.4 GTexel/s
FP32 (TFLOPS)
5.027 TFLOPS
8.141 TFLOPS
FP64 (TFLOPS)
157.1 GFLOPS (1:32)
254.4 GFLOPS (1:32)
FP16 (TFLOPS)
10.05 TFLOPS (2:1)
65.13 TFLOPS (8:1)
AI/RT
RT Cores
—
40
Tensor Cores
—
320
Power
TDP
125 W
70 W
TDP (W)
125
70
-44.0%
Suggested PSU
300 W
250 W
Power Connectors
1x 8-pin
None
Architecture
Architecture
Turing
Turing
GPU Name
TU116
TU104
Generation
Mining GPUs
Tesla Turing
(Txx)
Process Size
12 nm
12 nm
Transistors
6,600 million
13,600 million
Die Size
284 mm²
545 mm²
Foundry
TSMC
TSMC
Density
23.2M / mm²
25.0M / mm²
API Support
DirectX
12 (12_1)
12 Ultimate (12_2)
OpenGL
4.6
4.6
Vulkan
1.4
1.4
OpenCL
3.0
3.0
CUDA
7.5
7.5
Shader Model
6.8
6.8
Physical
Slot Width
Dual-slot
Single-slot
Length
229 mm
9 inches
168 mm
6.6 inches
Height
111 mm
4.4 inches
—
Outputs
No outputs
No outputs
Bus Interface
PCIe 1.0 x4
PCIe 3.0 x16
Other
Launch Price
799 USD
—
Production
End-of-life
End-of-life
Predecessor
—
Tesla Volta
Successor
—
Server Ampere