GeForce RTX 3070 vs Radeon Instinct MI308X
We compared two Desktop platform GPUs: 8GB VRAM GeForce RTX 3070 and 192GB VRAM Radeon Instinct MI308X to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
GeForce RTX 3070 's Advantages
Lower TDP (220W vs 750W)
Radeon Instinct MI308X 's Advantages
Released 3 years and 3 months late
Boost Clock has increased by 22% (2100MHz vs 1725MHz)
More VRAM (192GB vs 8GB)
Larger VRAM bandwidth (10.3TB/s vs 448.0GB/s)
13568 additional rendering cores
Score
Benchmark
FP32 (float)
GeForce RTX 3070
20310
Radeon Instinct MI308X
+302%
81720
Graphics Card
Sep 2020
Release Date
Dec 2023
GeForce 30
Generation
Radeon Instinct
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 5.0 x16
Clock Speeds
1500 MHz
Base Clock
1000 MHz
1725 MHz
Boost Clock
2100 MHz
1750 MHz
Memory Clock
2525 MHz
Memory
8GB
Memory Size
192GB
GDDR6
Memory Type
HBM3
256bit
Memory Bus
8192bit
448.0GB/s
Bandwidth
10.3TB/s
Render Config
-
Compute Units
304
46
SM Count
-
5888
Shading Units
19456
184
TMUs
1216
96
ROPs
0
184
Tensor Cores
1216
46
RT Cores
-
128 KB (per SM)
L1 Cache
16 KB (per CU)
4 MB
L2 Cache
16 MB
-
L3 Cache
256 MB
Theoretical Performance
165.6 GPixel/s
Pixel Rate
0 MPixel/s
317.4 GTexel/s
Texture Rate
2554 GTexel/s
20.31 TFLOPS
FP16 (half)
653.7 TFLOPS
20.31 TFLOPS
FP32 (float)
81.72 TFLOPS
317.4 GFLOPS
FP64 (double)
81.72 TFLOPS
Board Design
220W
TDP
750W
550 W
Suggested PSU
1150 W
1x HDMI 2.1
3x DisplayPort 1.4a
Outputs
No outputs
1x 12-pin
Power Connectors
None
Graphics Processor
GA104
GPU Name
Aqua Vanjaram
GA104-300-A1
GPU Variant
-
Ampere
Architecture
CDNA 3.0
Samsung
Foundry
TSMC
8 nm
Process Size
5 nm
17.4 billion
Transistors
153 billion
392 mm²
Die Size
1017 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
N/A
4.6
OpenGL
N/A
3.0
OpenCL
3.0
1.3
Vulkan
N/A
8.6
CUDA
-
6.6
Shader Model
N/A