NVIDIA GRID RTX T10 4 vs NVIDIA Quadro P6000
We compared two Professional market GPUs: 4GB VRAM GRID RTX T10 4 and 24GB VRAM Quadro P6000 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA GRID RTX T10 4 's Advantages
Released 3 years and 3 months late
Larger VRAM bandwidth (672.0GB/s vs 432.8GB/s)
Lower TDP (150W vs 250W)
NVIDIA Quadro P6000 's Advantages
Boost Clock has increased by 18% (1645MHz vs 1395MHz)
More VRAM (24GB vs 4GB)
256 additional rendering cores
Score
Benchmark
FP32 (float)
GRID RTX T10 4
9.999 TFLOPS
Quadro P6000
+26%
12.63 TFLOPS
Graphics Card
Jan 2020
Release Date
Oct 2016
GRID
Generation
Quadro Pascal
Professional
Type
Professional
PCIe 3.0 x16
Bus Interface
PCIe 3.0 x16
Clock Speeds
1065 MHz
Base Clock
1506 MHz
1395 MHz
Boost Clock
1645 MHz
1750 MHz
Memory Clock
1127 MHz
Memory
4GB
Memory Size
24GB
GDDR6
Memory Type
GDDR5X
384bit
Memory Bus
384bit
672.0GB/s
Bandwidth
432.8GB/s
Render Config
-
-
-
56
SM Count
30
3584
Shading Units
3840
224
TMUs
240
64
ROPs
96
448
Tensor Cores
-
56
RT Cores
-
64 KB (per SM)
L1 Cache
48 KB (per SM)
6 MB
L2 Cache
3 MB
-
-
-
Theoretical Performance
89.28 GPixel/s
Pixel Rate
157.9 GPixel/s
312.5 GTexel/s
Texture Rate
394.8 GTexel/s
20.00 TFLOPS
FP16 (half)
197.4 GFLOPS
9.999 TFLOPS
FP32 (float)
12.63 TFLOPS
312.5 GFLOPS
FP64 (double)
394.8 GFLOPS
Board Design
150W
TDP
250W
450 W
Suggested PSU
600 W
No outputs
Outputs
1x DVI
4x DisplayPort 1.4a
1x 6-pin + 1x 8-pin
Power Connectors
1x 8-pin
Graphics Processor
TU102
GPU Name
GP102
TU102-875-A1
GPU Variant
GP102-875-A1
Turing
Architecture
Pascal
TSMC
Foundry
TSMC
12 nm
Process Size
16 nm
18.6 billion
Transistors
11.8 billion
754 mm²
Die Size
471 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 (12_1)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.3
Vulkan
1.3
7.5
CUDA
6.1
6.8
Shader Model
6.7
