AMD Instinct MI300X vs NVIDIA L40 CNX
GPU · Specs Compare
Graphics Card
Release Date
Dec 2023
Oct 2022
Generation
Radeon Instinct
Tesla Ada
Type
Professional
Professional
Bus Interface
PCIe 5.0 x16
PCIe 4.0 x16
Clock Speeds
Base Clock
1000 MHz
1005 MHz
Boost Clock
2100 MHz
2475 MHz
Memory Clock
2525 MHz
2250 MHz
Memory
Memory Size
192GB
24GB
Memory Type
HBM3
GDDR6
Memory Bus
8192bit
384bit
Bandwidth
10.3TB/s
864.0GB/s
Render Config
Compute Units
304
—
Shading Units
19456
18176
TMUs
1216
568
ROPs
0
192
L1 Cache
16 KB (per CU)
128 KB (per SM)
L2 Cache
16 MB
48 MB
L3 Cache
256 MB
—
SM Count
—
142
Tensor Cores
—
568
RT Cores
—
142
Theoretical Performance
Pixel Rate
0 MPixel/s
475.2 GPixel/s
Texture Rate
2553.6 GTexel/s
1406 GTexel/s
FP16 (half)
653.7 TFLOPS
89.97 TFLOPS
FP32 (float)
81.72 TFLOPS
89.97 TFLOPS
FP64 (double)
81.72 TFLOPS
1406 GFLOPS
Graphics Processor
GPU Name
Aqua Vanjaram
AD102
Architecture
CDNA 3.0
Ada Lovelace
Foundry
TSMC
TSMC
Process Size
5 nm
4 nm
Transistors
153 billion
76.3 billion
Die Size
1017 mm²
608 mm²
GPU Variant
—
AD102-???-A1
Board Design
TDP
750W
300W
Suggested PSU
1150 W
700 W
Outputs
No outputs
1x HDMI 2.13x DisplayPort 1.4a
Power Connectors
None
1x 16-pin
Graphics Features
DirectX
N/A
12 Ultimate (12_2)
OpenGL
N/A
4.6
OpenCL
3.0
3.0
Vulkan
N/A
1.3
Shader Model
N/A
6.6
CUDA
—
8.9
▲ Specs Compare
Data sourced from official specifications and benchmark tests.