GPU Comparison
RADEON
AMD Radeon Instinct MI300A
CORE STATE
Aqua Vanjaram
VRAM
192 GB
CLOCK SPEED
2100 MHz
TDP
750 W
BUS WIDTH
8192 bit
ARCHITECTURE
CDNA 3.0
PROCESS
5 nm
LAUNCH DATE
2023
VS
GEFORCE
GeForce RTX 4010
CORE STATE
GA107
VRAM
4 GB
CLOCK SPEED
1762 MHz
TDP
50 W
BUS WIDTH
64 bit
ARCHITECTURE
Ampere
PROCESS
8 nm
LAUNCH DATE
2024
DETAILED SPECIFICATIONS
SPECIFICATION
Instinct MI300A
RTX 4010
Core Specs
Shading Units
19,456
768
-96.1%
Shaders
19,456
768
-96.1%
TMUs
1,216
24
-98.0%
ROPs
0
16
+∞%
Compute Units
304
—
SM Count
—
6
Clocks
Base Clock
1000 MHz
1417 MHz
Boost Clock
2100 MHz
1762 MHz
Memory Clock
2525 MHz
10.1 Gbps effective
1500 MHz
12 Gbps effective
Memory
Memory Size
192 GB
4 GB
VRAM (MB)
196,608
4,096
-97.9%
Memory Type
HBM3
GDDR6
Memory Bus
8192 bit
64 bit
Bandwidth
10.3 TB/s
96.00 GB/s
Cache
L1 Cache
16 KB (per CU)
128 KB (per SM)
L2 Cache
16 MB
2 MB
L3 Cache
256 MB
—
Performance
Pixel Rate
0 MPixel/s
28.19 GPixel/s
Texture Rate
2,553.6 GTexel/s
42.29 GTexel/s
FP32 (TFLOPS)
81.72 TFLOPS
2.706 TFLOPS
FP64 (TFLOPS)
81.72 TFLOPS (1:1)
42.29 GFLOPS (1:64)
FP16 (TFLOPS)
653.7 TFLOPS (8:1)
2.706 TFLOPS (1:1)
AI/RT
RT Cores
—
6
Tensor Cores
—
24
Matrix Cores
1,216
—
Power
TDP
750 W
50 W
TDP (W)
750
50
-93.3%
Suggested PSU
1150 W
250 W
Power Connectors
None
None
Architecture
Architecture
CDNA 3.0
Ampere
GPU Name
Aqua Vanjaram
GA107
Generation
Radeon Instinct
(MIx)
GeForce 40
Process Size
5 nm
8 nm
Transistors
153,000 million
8,700 million
Die Size
1017 mm²
200 mm²
Foundry
TSMC
Samsung
Density
150.4M / mm²
43.5M / mm²
AMD MCM
MCM
2
—
API Support
DirectX
—
12 Ultimate (12_2)
OpenGL
—
4.6
Vulkan
—
1.4
OpenCL
3.0
3.0
CUDA
—
8.6
Shader Model
—
6.8
Physical
Slot Width
OAM Module
Single-slot
Length
—
163 mm
6.4 inches
Height
—
69 mm
2.7 inches
Outputs
No outputs
4x mini-DisplayPort 1.4a
Bus Interface
PCIe 5.0 x16
PCIe 4.0 x8
Other
Production
—
Active
Predecessor
FirePro Data Center
GeForce 30
Successor
—
GeForce 50