GPU Comparison
GEFORCE
NVIDIA GeForce GTX 870M
CORE STATE
GK104
VRAM
3 GB
CLOCK SPEED
967 MHz
TDP
100 W
BUS WIDTH
192 bit
ARCHITECTURE
Kepler
PROCESS
28 nm
LAUNCH DATE
2014
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 870M
Tesla T4
Core Specs
Shading Units
1,344
2,560
+90.5%
Shaders
1,344
2,560
+90.5%
TMUs
112
160
+42.9%
ROPs
24
64
+166.7%
SM Count
—
40
Clocks
Base Clock
941 MHz
585 MHz
Boost Clock
967 MHz
1590 MHz
Memory Clock
1250 MHz
5 Gbps effective
1250 MHz
10 Gbps effective
Memory
Memory Size
3 GB
16 GB
VRAM (MB)
3,072
16,384
+433.3%
Memory Type
GDDR5
GDDR6
Memory Bus
192 bit
256 bit
Bandwidth
120.0 GB/s
320.0 GB/s
Cache
L1 Cache
16 KB (per SMX)
64 KB (per SM)
L2 Cache
384 KB
4 MB
Performance
Pixel Rate
27.08 GPixel/s
101.8 GPixel/s
Texture Rate
108.3 GTexel/s
254.4 GTexel/s
FP32 (TFLOPS)
2.599 TFLOPS
8.141 TFLOPS
FP64 (TFLOPS)
108.3 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
100 W
70 W
TDP (W)
100
70
-30.0%
Suggested PSU
—
250 W
Power Connectors
None
None
Architecture
Architecture
Kepler
Turing
GPU Name
GK104
TU104
Generation
GeForce 800M
Tesla Turing
(Txx)
Process Size
28 nm
12 nm
Transistors
3,540 million
13,600 million
Die Size
294 mm²
545 mm²
Foundry
TSMC
TSMC
Density
12.0M / 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
MXM Module
Single-slot
Length
—
168 mm
6.6 inches
Outputs
Portable Device Dependent
No outputs
Bus Interface
MXM-B (3.0)
PCIe 3.0 x16
Other
Production
End-of-life
End-of-life
Predecessor
GeForce 700M
Tesla Volta
Successor
GeForce 900M
Server Ampere