NVIDIA GeForce RTX 4070 Max-Q vs AMD Radeon Instinct MI350X

GPU · Specs Compare

Products
GPU NVIDIA GeForce RTX 4070 Max-Q NVIDIA · 2023-01
GPU AMD Radeon Instinct MI350X AMD · 2025-01
Graphics Card
Release Date
Jan 2023
Jun 2025
Generation
GeForce 40 Mobile
Radeon Instinct
Type
Mobile
Professional
Bus Interface
PCIe 4.0 x8
PCIe 5.0 x16
Clock Speeds
Base Clock
735 MHz
1000 MHz
Boost Clock
1230 MHz
2200 MHz
Memory Clock
2000 MHz
2000 MHz
Memory
Memory Size
8GB
288GB
Memory Type
GDDR6
HBM3e
Memory Bus
128bit
8192bit
Bandwidth
256.0GB/s
8.19TB/s
Render Config
SM Count
36
—
Shading Units
4608
16384
TMUs
144
1024
ROPs
48
0
Tensor Cores
144
1024
RT Cores
36
—
L1 Cache
128 KB (per SM)
16 KB (per CU)
L2 Cache
32 MB
16 MB
Compute Units
—
256
L3 Cache
—
256 MB
Theoretical Performance
Pixel Rate
59.04 GPixel/s
0 MPixel/s
Texture Rate
177.1 GTexel/s
2252.8 GTexel/s
FP16 (half)
11.34 TFLOPS
72.09 TFLOPS
FP32 (float)
11.34 TFLOPS
72.09 TFLOPS
FP64 (double)
177.1 GFLOPS
36.04 TFLOPS
Graphics Processor
GPU Name
AD106
MI350 256CU
GPU Variant
GN21-X6
—
Architecture
Ada Lovelace
CDNA 4.0
Foundry
TSMC
TSMC
Process Size
5 nm
3 nm
Transistors
22.9 billion
185 billion
Die Size
188 mm²
Unknown
Board Design
TDP
35W
1000W
Outputs
Portable Device Dependent
No outputs
Power Connectors
None
None
Suggested PSU
—
1400 W
Graphics Features
DirectX
12 Ultimate (12_2)
N/A
OpenGL
4.6
N/A
OpenCL
3.0
3.0
Vulkan
1.3
N/A
CUDA
8.9
—
Shader Model
6.8
N/A
▲ Specs Compare Data sourced from official specifications and benchmark tests.