GPU Comparison
GEFORCE
NVIDIA GeForce GTX 650
CORE STATE
GK106
VRAM
1024 MB
CLOCK SPEED
—
TDP
65 W
BUS WIDTH
128 bit
ARCHITECTURE
Kepler
PROCESS
28 nm
LAUNCH DATE
2013
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_metal
geekbench_opencl
geekbench_vulkan
DETAILED SPECIFICATIONS
SPECIFICATION
GTX 650
Tesla T4
Core Specs
Shading Units
384
2,560
+566.7%
Shaders
384
2,560
+566.7%
TMUs
32
160
+400.0%
ROPs
16
64
+300.0%
SM Count
—
40
Clocks
Base Clock
—
585 MHz
Boost Clock
—
1590 MHz
GPU Clock
1058 MHz
—
Memory Clock
1250 MHz
5 Gbps effective
1250 MHz
10 Gbps effective
Memory
Memory Size
1024 MB
16 GB
VRAM (MB)
1,024
16,384
+1500.0%
Memory Type
GDDR5
GDDR6
Memory Bus
128 bit
256 bit
Bandwidth
80.00 GB/s
320.0 GB/s
Cache
L1 Cache
16 KB (per SMX)
64 KB (per SM)
L2 Cache
256 KB
4 MB
Performance
Pixel Rate
8.464 GPixel/s
101.8 GPixel/s
Texture Rate
33.86 GTexel/s
254.4 GTexel/s
FP32 (TFLOPS)
812.5 GFLOPS
8.141 TFLOPS
FP64 (TFLOPS)
33.86 GFLOPS (1:24)
254.4 GFLOPS (1:32)
FP16 (TFLOPS)
—
65.13 TFLOPS (8:1)
AI/RT
RT Cores
—
40
Tensor Cores
—
320
Power
TDP
65 W
70 W
TDP (W)
65
70
+7.7%
Suggested PSU
250 W
250 W
Power Connectors
1x 6-pin
None
Architecture
Architecture
Kepler
Turing
GPU Name
GK106
TU104
Generation
GeForce 600
Tesla Turing
(Txx)
Process Size
28 nm
12 nm
Transistors
2,540 million
13,600 million
Die Size
221 mm²
545 mm²
Foundry
TSMC
TSMC
Density
11.5M / mm²
25.0M / mm²
API Support
DirectX
12 (11_0)
12 Ultimate (12_2)
OpenGL
4.6
4.6
Vulkan
1.2.175
1.4
OpenCL
3.0
3.0
CUDA
3.0
7.5
Shader Model
6.5 (5.1)
6.8
Physical
Slot Width
Single-slot
Single-slot
Length
147 mm
5.8 inches
168 mm
6.6 inches
Outputs
1x DVI2x DisplayPort 1.2
No outputs
Bus Interface
PCIe 3.0 x16
PCIe 3.0 x16
Other
Production
End-of-life
End-of-life
Predecessor
GeForce 500
Tesla Volta
Successor
GeForce 700
Server Ampere