NVIDIA GeForce RTX 4070 vs AMD Radeon Instinct MI308X
We compared two Desktop platform GPUs: 12GB VRAM GeForce RTX 4070 and 192GB VRAM Radeon Instinct MI308X to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA GeForce RTX 4070 's Advantages
Boost Clock has increased by 18% (2475MHz vs 2100MHz)
Lower TDP (200W vs 750W)
AMD Radeon Instinct MI308X 's Advantages
Released 8 months late
More VRAM (192GB vs 12GB)
Larger VRAM bandwidth (10.3TB/s vs 504.2GB/s)
13568 additional rendering cores
Score
Benchmark
FP32 (float)
GeForce RTX 4070
29.15 TFLOPS
Radeon Instinct MI308X
+180%
81.72 TFLOPS
Graphics Card
Apr 2023
Release Date
Dec 2023
GeForce 40
Generation
Radeon Instinct
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 5.0 x16
Clock Speeds
1920 MHz
Base Clock
1000 MHz
2475 MHz
Boost Clock
2100 MHz
1313 MHz
Memory Clock
2525 MHz
Memory
12GB
Memory Size
192GB
GDDR6X
Memory Type
HBM3
192bit
Memory Bus
8192bit
504.2GB/s
Bandwidth
10.3TB/s
Render Config
-
Compute Units
304
46
SM Count
-
5888
Shading Units
19456
184
TMUs
1216
64
ROPs
0
184
Tensor Cores
1216
46
RT Cores
-
128 KB (per SM)
L1 Cache
16 KB (per CU)
36 MB
L2 Cache
16 MB
-
L3 Cache
256 MB
Theoretical Performance
158.4 GPixel/s
Pixel Rate
0 MPixel/s
455.4 GTexel/s
Texture Rate
2554 GTexel/s
29.15 TFLOPS
FP16 (half)
653.7 TFLOPS
29.15 TFLOPS
FP32 (float)
81.72 TFLOPS
455.4 GFLOPS
FP64 (double)
81.72 TFLOPS
Board Design
200W
TDP
750W
550 W
Suggested PSU
1150 W
1x HDMI 2.1
3x DisplayPort 1.4a
Outputs
No outputs
1x 16-pin
Power Connectors
None
Graphics Processor
AD104
GPU Name
Aqua Vanjaram
AD104-250-A1
GPU Variant
-
Ada Lovelace
Architecture
CDNA 3.0
TSMC
Foundry
TSMC
5 nm
Process Size
5 nm
35.8 billion
Transistors
153 billion
295 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
8.9
CUDA
-
6.7
Shader Model
N/A
