GPU Comparison
GPU
Intel Data Center GPU Max 1350
CORE STATE
Ponte Vecchio
VRAM
96 GB
CLOCK SPEED
1550 MHz
TDP
450 W
BUS WIDTH
8192 bit
ARCHITECTURE
Generation 12.5
PROCESS
10 nm
LAUNCH DATE
2023
VS
GEFORCE
GeForce RTX 3050 8 GB GA107
CORE STATE
GA107
VRAM
8 GB
CLOCK SPEED
1777 MHz
TDP
115 W
BUS WIDTH
128 bit
ARCHITECTURE
Ampere
PROCESS
8 nm
LAUNCH DATE
2022
DETAILED SPECIFICATIONS
SPECIFICATION
Data Center GPU Max 1350
RTX 3050 8 GB GA107
Core Specs
Shading Units
14,336
2,560
-82.1%
Shaders
14,336
2,560
-82.1%
TMUs
896
80
-91.1%
ROPs
0
32
+∞%
SM Count
—
20
Execution Units
896
—
Clocks
Base Clock
750 MHz
1552 MHz
Boost Clock
1550 MHz
1777 MHz
Memory Clock
1200 MHz
2.4 Gbps effective
1750 MHz
14 Gbps effective
Memory
Memory Size
96 GB
8 GB
VRAM (MB)
98,304
8,192
-91.7%
Memory Type
HBM2e
GDDR6
Memory Bus
8192 bit
128 bit
Bandwidth
2.46 TB/s
224.0 GB/s
Cache
L1 Cache
64 KB (per EU)
128 KB (per SM)
L2 Cache
408 MB
2 MB
Performance
Pixel Rate
0 MPixel/s
56.86 GPixel/s
Texture Rate
1,388.8 GTexel/s
142.2 GTexel/s
FP32 (TFLOPS)
44.44 TFLOPS
9.098 TFLOPS
FP64 (TFLOPS)
44.44 TFLOPS (1:1)
142.2 GFLOPS (1:64)
FP16 (TFLOPS)
44.44 TFLOPS (1:1)
9.098 TFLOPS (1:1)
AI/RT
RT Cores
112
20
-82.1%
Tensor Cores
—
80
XMX Cores
896
—
Power
TDP
450 W
115 W
TDP (W)
450
115
-74.4%
Suggested PSU
850 W
300 W
Power Connectors
—
1x 6-pin
Architecture
Architecture
Generation 12.5
Ampere
GPU Name
Ponte Vecchio
GA107
Generation
Data Center GPU
(Ponte Vecchio)
GeForce 30
Process Size
10 nm
8 nm
Transistors
100,000 million
8,700 million
Die Size
1280 mm²
200 mm²
Foundry
Intel
Samsung
Density
78.1M / mm²
43.5M / mm²
API Support
DirectX
12 (12_1)
12 Ultimate (12_2)
OpenGL
4.6
4.6
Vulkan
—
1.4
OpenCL
3.0
3.0
CUDA
—
8.6
Shader Model
6.6
6.8
Physical
Slot Width
OAM Module
Dual-slot
Length
—
242 mm
9.5 inches
Height
—
112 mm
4.4 inches
Outputs
No outputs
1x HDMI 2.13x DisplayPort 1.4a
Bus Interface
PCIe 5.0 x16
PCIe 4.0 x8
Other
Launch Price
—
249 USD
Production
Active
End-of-life
Predecessor
—
GeForce 20
Successor
H3C Graphics
GeForce 40