NVIDIA GRID RTX T10 4 vs NVIDIA Tesla S870
We compared two Professional market GPUs: 4GB VRAM GRID RTX T10 4 and 1536MB VRAM Tesla S870 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 12 years and 8 months late
Boost Clock1395MHz
More VRAM (4GB vs 1536GB)
Larger VRAM bandwidth (672.0GB/s vs 76.80GB/s)
3456 additional rendering cores
Lower TDP (150W vs 800W)
Score
Benchmark
FP32 (float)
GRID RTX T10 4
+2789%
9.999 TFLOPS
Tesla S870
0.346 TFLOPS
Graphics Card
Jan 2020
Release Date
May 2007
GRID
Generation
Tesla
Professional
Type
Professional
PCIe 3.0 x16
Bus Interface
PCIe 1.0 x16
Clock Speeds
1065 MHz
Base Clock
-
1395 MHz
Boost Clock
-
1750 MHz
Memory Clock
800 MHz
Memory
4GB
Memory Size
1536MB
GDDR6
Memory Type
GDDR3
384bit
Memory Bus
384bit
672.0GB/s
Bandwidth
76.80GB/s
Render Config
-
-
-
56
SM Count
16
3584
Shading Units
128
224
TMUs
32
64
ROPs
24
448
Tensor Cores
-
56
RT Cores
-
64 KB (per SM)
L1 Cache
-
6 MB
L2 Cache
96 KB
-
-
-
Theoretical Performance
89.28 GPixel/s
Pixel Rate
14.40 GPixel/s
312.5 GTexel/s
Texture Rate
38.40 GTexel/s
20.00 TFLOPS
FP16 (half)
-
9.999 TFLOPS
FP32 (float)
345.6 GFLOPS
312.5 GFLOPS
FP64 (double)
-
Board Design
150W
TDP
800W
450 W
Suggested PSU
1200 W
No outputs
Outputs
No outputs
1x 6-pin + 1x 8-pin
Power Connectors
-
Graphics Processor
TU102
GPU Name
G80
TU102-875-A1
GPU Variant
-
Turing
Architecture
Tesla
TSMC
Foundry
TSMC
12 nm
Process Size
90 nm
18.6 billion
Transistors
0.681 billion
754 mm²
Die Size
484 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
11.1 (10_0)
4.6
OpenGL
3.3
3.0
OpenCL
1.1 (1.0)
1.3
Vulkan
N/A
7.5
CUDA
1.0
6.8
Shader Model
4.0
