NVIDIA GRID RTX T10 4 vs NVIDIA Tesla M6
We compared two Professional market GPUs: 4GB VRAM GRID RTX T10 4 and 8GB VRAM Tesla M6 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 4 years and 5 months late
Boost Clock has increased by 18% (1395MHz vs 1180MHz)
Larger VRAM bandwidth (672.0GB/s vs 160.4GB/s)
2048 additional rendering cores
NVIDIA Tesla M6 's Advantages
More VRAM (8GB vs 4GB)
Lower TDP (100W vs 150W)
Score
Benchmark
FP32 (float)
GRID RTX T10 4
+175%
9.999 TFLOPS
Tesla M6
3.625 TFLOPS
Graphics Card
Jan 2020
Release Date
Aug 2015
GRID
Generation
Tesla
Professional
Type
Professional
PCIe 3.0 x16
Bus Interface
PCIe 3.0 x16
Clock Speeds
1065 MHz
Base Clock
930 MHz
1395 MHz
Boost Clock
1180 MHz
1750 MHz
Memory Clock
1253 MHz
Memory
4GB
Memory Size
8GB
GDDR6
Memory Type
GDDR5
384bit
Memory Bus
256bit
672.0GB/s
Bandwidth
160.4GB/s
Render Config
-
-
-
56
SM Count
-
3584
Shading Units
1536
224
TMUs
96
64
ROPs
64
448
Tensor Cores
-
56
RT Cores
-
64 KB (per SM)
L1 Cache
48 KB (per SMM)
6 MB
L2 Cache
2 MB
-
-
-
Theoretical Performance
89.28 GPixel/s
Pixel Rate
75.52 GPixel/s
312.5 GTexel/s
Texture Rate
113.3 GTexel/s
20.00 TFLOPS
FP16 (half)
-
9.999 TFLOPS
FP32 (float)
3.625 TFLOPS
312.5 GFLOPS
FP64 (double)
113.3 GFLOPS
Board Design
150W
TDP
100W
450 W
Suggested PSU
300 W
No outputs
Outputs
No outputs
1x 6-pin + 1x 8-pin
Power Connectors
None
Graphics Processor
TU102
GPU Name
GM204
TU102-875-A1
GPU Variant
GM204-995-A1
Turing
Architecture
Maxwell 2.0
TSMC
Foundry
TSMC
12 nm
Process Size
28 nm
18.6 billion
Transistors
5.2 billion
754 mm²
Die Size
398 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
5.2
6.8
Shader Model
6.4
