GPU Comparison
RADEON
AMD Radeon Instinct MI300
CORE STATE
Aqua Vanjaram
VRAM
128 GB
CLOCK SPEED
1700 MHz
TDP
600 W
BUS WIDTH
8192 bit
ARCHITECTURE
CDNA 3.0
PROCESS
5 nm
LAUNCH DATE
2023
VS
GEFORCE
GeForce RTX 4090 Max-Q
CORE STATE
AD103
VRAM
16 GB
CLOCK SPEED
1455 MHz
TDP
80 W
BUS WIDTH
256 bit
ARCHITECTURE
Ada Lovelace
PROCESS
5 nm
LAUNCH DATE
2023
DETAILED SPECIFICATIONS
SPECIFICATION
Instinct MI300
RTX 4090 Max-Q
Core Specs
Shading Units
14,080
9,728
-30.9%
Shaders
14,080
9,728
-30.9%
TMUs
880
304
-65.5%
ROPs
0
112
+∞%
Compute Units
220
—
SM Count
—
76
Clocks
Base Clock
1000 MHz
930 MHz
Boost Clock
1700 MHz
1455 MHz
Memory Clock
1600 MHz
6.4 Gbps effective
2250 MHz
18 Gbps effective
Memory
Memory Size
128 GB
16 GB
VRAM (MB)
131,072
16,384
-87.5%
Memory Type
HBM3
GDDR6
Memory Bus
8192 bit
256 bit
Bandwidth
6.55 TB/s
576.0 GB/s
Cache
L1 Cache
16 KB (per CU)
128 KB (per SM)
L2 Cache
16 MB
64 MB
Performance
Pixel Rate
0 MPixel/s
163.0 GPixel/s
Texture Rate
1,496.0 GTexel/s
442.3 GTexel/s
FP32 (TFLOPS)
47.87 TFLOPS
28.31 TFLOPS
FP64 (TFLOPS)
47.87 TFLOPS (1:1)
442.3 GFLOPS (1:64)
FP16 (TFLOPS)
383.0 TFLOPS (8:1)
28.31 TFLOPS (1:1)
AI/RT
RT Cores
—
76
Tensor Cores
—
304
Matrix Cores
880
—
Power
TDP
600 W
80 W
TDP (W)
600
80
-86.7%
Suggested PSU
1000 W
—
Power Connectors
2x 8-pin
None
Architecture
Architecture
CDNA 3.0
Ada Lovelace
GPU Name
Aqua Vanjaram
AD103
Generation
Radeon Instinct
(MIx)
GeForce 40 Mobile
Process Size
5 nm
5 nm
Transistors
153,000 million
45,900 million
Die Size
1017 mm²
379 mm²
Foundry
TSMC
TSMC
Density
150.4M / mm²
121.1M / mm²
AMD MCM
MCM
2
—
API Support
DirectX
—
12 Ultimate (12_2)
OpenGL
—
4.6
Vulkan
—
1.4
OpenCL
3.0
3.0
CUDA
—
8.9
Shader Model
—
6.8
Physical
Slot Width
—
IGP
Length
267 mm
10.5 inches
—
Height
111 mm
4.4 inches
—
Outputs
No outputs
Portable Device Dependent
Bus Interface
PCIe 5.0 x16
PCIe 4.0 x16
Other
Production
—
Active
Predecessor
FirePro Data Center
GeForce 30 Mobile
Successor
—
GeForce 50 Mobile