NVIDIA RTX 4000 SFF Ada Generation vs NVIDIA GeForce RTX 3090
GPU · Specs Compare
Graphics Card
Release Date
Nov 2018
Sep 2020
Generation
Radeon Instinct
GeForce 30
Type
Professional
Desktop
Bus Interface
PCIe 4.0 x16
PCIe 4.0 x16
Clock Speeds
Base Clock
1200 MHz
1395 MHz
Boost Clock
1746 MHz
1695 MHz
Memory Clock
1000 MHz
1219 MHz
Memory
Memory Size
16GB
24GB
Memory Type
HBM2
GDDR6X
Memory Bus
4096bit
384bit
Bandwidth
1.02TB/s
936.2GB/s
Render Config
SM Count
48
82
Compute Units
60
—
Shading Units
3840
10496
TMUs
240
328
ROPs
64
112
Tensor Cores
192
328
RT Cores
48
82
L1 Cache
16 KB (per CU)
128 KB (per SM)
L2 Cache
4 MB
6 MB
Theoretical Performance
Pixel Rate
111.7 GPixel/s
189.8 GPixel/s
Texture Rate
419.0 GTexel/s
556.0 GTexel/s
FP16 (half)
26.82 TFLOPS
35.58 TFLOPS
FP32 (float)
13.41 TFLOPS
35.58 TFLOPS
FP64 (double)
6.705 TFLOPS
556.0 GFLOPS
Graphics Processor
GPU Name
Vega 20
GA102
GPU Variant
Vega 20 GLXT
GA102-300-A1
Architecture
GCN 5.1
Ampere
Foundry
TSMC
Samsung
Process Size
7 nm
8 nm
Transistors
13.23 billion
28.3 billion
Die Size
331 mm²
628 mm²
Board Design
TDP
300W
350W
Suggested PSU
700 W
750 W
Outputs
1x mini-DisplayPort 1.4a
1x HDMI 2.13x DisplayPort 1.4a
Power Connectors
2x 8-pin
1x 12-pin
Graphics Features
DirectX
12 (12_1)
12 Ultimate (12_2)
OpenGL
4.6
4.6
OpenCL
2.1
3.0
Vulkan
1.3
1.3
CUDA
8.9
8.6
Shader Model
6.7
6.6
▲ Specs Compare
Data sourced from official specifications and benchmark tests.