NVIDIA GRID RTX T10 4 vs NVIDIA Tesla V100 DGXS 16 GB
We compared two Professional market GPUs: 4GB VRAM GRID RTX T10 4 and 16GB VRAM Tesla V100 DGXS 16 GB 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 1 years and 10 months late
Lower TDP (150W vs 250W)
NVIDIA Tesla V100 DGXS 16 GB 's Advantages
Boost Clock has increased by 10% (1530MHz vs 1395MHz)
More VRAM (16GB vs 4GB)
Larger VRAM bandwidth (897.0GB/s vs 672.0GB/s)
1536 additional rendering cores
Score
Benchmark
FP32 (float)
GRID RTX T10 4
9.999 TFLOPS
Tesla V100 DGXS 16 GB
+56%
15.67 TFLOPS
Graphics Card
Jan 2020
Release Date
Mar 2018
GRID
Generation
Tesla
Professional
Type
Professional
PCIe 3.0 x16
Bus Interface
PCIe 3.0 x16
Clock Speeds
1065 MHz
Base Clock
1327 MHz
1395 MHz
Boost Clock
1530 MHz
1750 MHz
Memory Clock
876 MHz
Memory
4GB
Memory Size
16GB
GDDR6
Memory Type
HBM2
384bit
Memory Bus
4096bit
672.0GB/s
Bandwidth
897.0GB/s
Render Config
-
-
-
56
SM Count
80
3584
Shading Units
5120
224
TMUs
320
64
ROPs
128
448
Tensor Cores
640
56
RT Cores
-
64 KB (per SM)
L1 Cache
128 KB (per SM)
6 MB
L2 Cache
6 MB
-
-
-
Theoretical Performance
89.28 GPixel/s
Pixel Rate
195.8 GPixel/s
312.5 GTexel/s
Texture Rate
489.6 GTexel/s
20.00 TFLOPS
FP16 (half)
31.33 TFLOPS
9.999 TFLOPS
FP32 (float)
15.67 TFLOPS
312.5 GFLOPS
FP64 (double)
7.834 TFLOPS
Board Design
150W
TDP
250W
450 W
Suggested PSU
600 W
No outputs
Outputs
No outputs
1x 6-pin + 1x 8-pin
Power Connectors
None
Graphics Processor
TU102
GPU Name
GV100
TU102-875-A1
GPU Variant
-
Turing
Architecture
Volta
TSMC
Foundry
TSMC
12 nm
Process Size
12 nm
18.6 billion
Transistors
21.1 billion
754 mm²
Die Size
815 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
7.0
6.8
Shader Model
6.6
