AMD Radeon Instinct MI25 vs NVIDIA GRID RTX T10 2
We compared two Professional market GPUs: 16GB VRAM Radeon Instinct MI25 and 2GB VRAM GRID RTX T10 2 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
AMD Radeon Instinct MI25 's Advantages
Boost Clock has increased by 8% (1500MHz vs 1395MHz)
More VRAM (16GB vs 2GB)
512 additional rendering cores
NVIDIA GRID RTX T10 2 's Advantages
Released 2 years and 7 months late
Larger VRAM bandwidth (672.0GB/s vs 436.2GB/s)
Lower TDP (150W vs 300W)
Score
Benchmark
FP32 (float)
Radeon Instinct MI25
+22%
12.29 TFLOPS
GRID RTX T10 2
9.999 TFLOPS
Graphics Card
Jun 2017
Release Date
Jan 2020
Radeon Instinct
Generation
GRID
Professional
Type
Professional
PCIe 3.0 x16
Bus Interface
PCIe 3.0 x16
Clock Speeds
1400 MHz
Base Clock
1065 MHz
1500 MHz
Boost Clock
1395 MHz
852 MHz
Memory Clock
1750 MHz
Memory
16GB
Memory Size
2GB
HBM2
Memory Type
GDDR6
2048bit
Memory Bus
384bit
436.2GB/s
Bandwidth
672.0GB/s
Render Config
64
Compute Units
-
-
SM Count
56
4096
Shading Units
3584
256
TMUs
224
64
ROPs
64
-
Tensor Cores
448
-
RT Cores
56
16 KB (per CU)
L1 Cache
64 KB (per SM)
4 MB
L2 Cache
6 MB
-
-
-
Theoretical Performance
96.00 GPixel/s
Pixel Rate
89.28 GPixel/s
384.0 GTexel/s
Texture Rate
312.5 GTexel/s
24.58 TFLOPS
FP16 (half)
20.00 TFLOPS
12.29 TFLOPS
FP32 (float)
9.999 TFLOPS
768.0 GFLOPS
FP64 (double)
312.5 GFLOPS
Board Design
300W
TDP
150W
700 W
Suggested PSU
450 W
No outputs
Outputs
No outputs
2x 8-pin
Power Connectors
1x 6-pin + 1x 8-pin
Graphics Processor
Vega 10
GPU Name
TU102
Vega 10 XT GL
(215-0894124)
GPU Variant
TU102-875-A1
GCN 5.0
Architecture
Turing
GlobalFoundries
Foundry
TSMC
14 nm
Process Size
12 nm
12.5 billion
Transistors
18.6 billion
495 mm²
Die Size
754 mm²
Graphics Features
12 (12_1)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
2.1
OpenCL
3.0
1.2
Vulkan
1.3
-
CUDA
7.5
6.4
Shader Model
6.8
