GPU Comparison
GEFORCE
NVIDIA GeForce GTX 980
CORE STATE
GM204
VRAM
4 GB
CLOCK SPEED
1216 MHz
TDP
165 W
BUS WIDTH
256 bit
ARCHITECTURE
Maxwell 2.0
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
3dmark_3dmark_steel_nomad_dx12
geekbench_metal
geekbench_opencl
geekbench_vulkan
passmark_directx_10
passmark_directx_11
passmark_directx_12
passmark_directx_9
passmark_g2d
passmark_g3d
passmark_gpu_compute
DETAILED SPECIFICATIONS
SPECIFICATION
GTX 980
Tesla T4
Core Specs
Shading Units
2,048
2,560
+25.0%
Shaders
2,048
2,560
+25.0%
TMUs
128
160
+25.0%
ROPs
64
64
0.0%
SM Count
—
40
Clocks
Base Clock
1127 MHz
585 MHz
Boost Clock
1216 MHz
1590 MHz
Memory Clock
1753 MHz
7 Gbps effective
1250 MHz
10 Gbps effective
Memory
Memory Size
4 GB
16 GB
VRAM (MB)
4,096
16,384
+300.0%
Memory Type
GDDR5
GDDR6
Memory Bus
256 bit
256 bit
Bandwidth
224.4 GB/s
320.0 GB/s
Cache
L1 Cache
48 KB (per SMM)
64 KB (per SM)
L2 Cache
2 MB
4 MB
Performance
Pixel Rate
77.82 GPixel/s
101.8 GPixel/s
Texture Rate
155.6 GTexel/s
254.4 GTexel/s
FP32 (TFLOPS)
4.981 TFLOPS
8.141 TFLOPS
FP64 (TFLOPS)
155.6 GFLOPS (1:32)
254.4 GFLOPS (1:32)
FP16 (TFLOPS)
—
65.13 TFLOPS (8:1)
AI/RT
RT Cores
—
40
Tensor Cores
—
320
Power
TDP
165 W
70 W
TDP (W)
165
70
-57.6%
Suggested PSU
450 W
250 W
Power Connectors
2x 6-pin
None
Architecture
Architecture
Maxwell 2.0
Turing
GPU Name
GM204
TU104
Generation
GeForce 900
Tesla Turing
(Txx)
Process Size
28 nm
12 nm
Transistors
5,200 million
13,600 million
Die Size
398 mm²
545 mm²
Foundry
TSMC
TSMC
Density
13.1M / 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
5.2
7.5
Shader Model
6.8
6.8
Physical
Slot Width
Dual-slot
Single-slot
Length
267 mm
10.5 inches
168 mm
6.6 inches
Height
111 mm
4.4 inches
—
Outputs
1x DVI1x HDMI 2.03x DisplayPort 1.2
No outputs
Bus Interface
PCIe 3.0 x16
PCIe 3.0 x16
Other
Launch Price
549 USD
—
Production
End-of-life
End-of-life
Predecessor
GeForce 700
Tesla Volta
Successor
GeForce 10
Server Ampere