NVIDIA GeForce RTX 3050 8 GB GA107 vs NVIDIA RTX 4000 SFF Ada Generation
GPU · Specs Compare
Graphics Card
Release Date
Jan 2022
Nov 2018
Generation
GeForce 30
Radeon Instinct
Type
Desktop
Professional
Bus Interface
PCIe 4.0 x8
PCIe 4.0 x16
Clock Speeds
Base Clock
1552 MHz
1200 MHz
Boost Clock
1777 MHz
1746 MHz
Memory Clock
1750 MHz
1000 MHz
Memory
Memory Size
8GB
16GB
Memory Type
GDDR6
HBM2
Memory Bus
128bit
4096bit
Bandwidth
224.0GB/s
1.02TB/s
Render Config
SM Count
20
48
Shading Units
2560
3840
TMUs
80
240
ROPs
32
64
Tensor Cores
80
192
RT Cores
20
48
L1 Cache
128 KB (per SM)
16 KB (per CU)
L2 Cache
2 MB
4 MB
Compute Units
—
60
Theoretical Performance
Pixel Rate
56.86 GPixel/s
111.7 GPixel/s
Texture Rate
142.2 GTexel/s
419.0 GTexel/s
FP16 (half)
9.098 TFLOPS
26.82 TFLOPS
FP32 (float)
9.098 TFLOPS
13.41 TFLOPS
FP64 (double)
142.2 GFLOPS
6.705 TFLOPS
Graphics Processor
GPU Name
GA107
Vega 20
GPU Variant
GA107-150-A1
Vega 20 GLXT
Architecture
Ampere
GCN 5.1
Foundry
Samsung
TSMC
Process Size
8 nm
7 nm
Transistors
Unknown
13.23 billion
Die Size
Unknown
331 mm²
Board Design
TDP
115W
300W
Suggested PSU
300 W
700 W
Outputs
1x HDMI 2.13x DisplayPort 1.4a
1x mini-DisplayPort 1.4a
Power Connectors
1x 8-pin
2x 8-pin
Graphics Features
DirectX
12 Ultimate (12_2)
12 (12_1)
OpenGL
4.6
4.6
OpenCL
3.0
2.1
Vulkan
1.3
1.3
CUDA
8.6
8.9
Shader Model
6.6
6.7
Benchmark
3DMark Time Spy
7,384
—
3DMark Time Spy Extreme
3,391
—
▲ Specs Compare
Data sourced from official specifications and benchmark tests.