RTX 4000 Ada Generation vs RTX 4000 SFF Ada Generation
We compared a Desktop platform GPU: 20GB VRAM RTX 4000 Ada Generation and a Professional market GPU: 16GB VRAM RTX 4000 SFF Ada Generation to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
RTX 4000 Ada Generation 's Advantages
Released 4 years and 9 months late
Boost Clock has increased by 25% (2175MHz vs 1746MHz)
More VRAM (20GB vs 16GB)
2304 additional rendering cores
Lower TDP (130W vs 300W)
RTX 4000 SFF Ada Generation 's Advantages
Larger VRAM bandwidth (1.02TB/s vs 360.0GB/s)
Score
Benchmark
FP32 (float)
RTX 4000 Ada Generation
+99%
26730
RTX 4000 SFF Ada Generation
13410
3DMark Time Spy
RTX 4000 Ada Generation
+37%
14340
RTX 4000 SFF Ada Generation
10406
3DMark Time Spy Extreme
RTX 4000 Ada Generation
+40%
6708
RTX 4000 SFF Ada Generation
4783
3DMark Speed Way
RTX 4000 Ada Generation
+44%
3666
RTX 4000 SFF Ada Generation
2542
Blender
RTX 4000 Ada Generation
+27%
4737
RTX 4000 SFF Ada Generation
3717
OctaneBench
RTX 4000 Ada Generation
+11%
492
RTX 4000 SFF Ada Generation
443
Graphics Card
Aug 2023
Release Date
Nov 2018
Workstation Ada
Generation
Radeon Instinct
Desktop
Type
Professional
PCIe 4.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
1500 MHz
Base Clock
1200 MHz
2175 MHz
Boost Clock
1746 MHz
2250 MHz
Memory Clock
1000 MHz
Memory
20GB
Memory Size
16GB
GDDR6
Memory Type
HBM2
160bit
Memory Bus
4096bit
360.0GB/s
Bandwidth
1.02TB/s
Render Config
-
Compute Units
60
48
SM Count
48
6144
Shading Units
3840
192
TMUs
240
64
ROPs
64
192
Tensor Cores
192
48
RT Cores
48
128 KB (per SM)
L1 Cache
16 KB (per CU)
48 MB
L2 Cache
4 MB
Theoretical Performance
139.2 GPixel/s
Pixel Rate
111.7 GPixel/s
417.6 GTexel/s
Texture Rate
419.0 GTexel/s
26.73 TFLOPS
FP16 (half)
26.82 TFLOPS
26.73 TFLOPS
FP32 (float)
13.41 TFLOPS
417.6 GFLOPS
FP64 (double)
6.705 TFLOPS
Board Design
130W
TDP
300W
300 W
Suggested PSU
700 W
4x DisplayPort 1.4a
Outputs
1x mini-DisplayPort 1.4a
1x 16-pin
Power Connectors
2x 8-pin
Graphics Processor
AD104
GPU Name
Vega 20
-
GPU Variant
Vega 20 GLXT
Ada Lovelace
Architecture
GCN 5.1
TSMC
Foundry
TSMC
5 nm
Process Size
7 nm
35.8 billion
Transistors
13.23 billion
294 mm²
Die Size
331 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 (12_1)
4.6
OpenGL
4.6
3.0
OpenCL
2.1
1.3
Vulkan
1.3
8.9
CUDA
8.9
6.8
Shader Model
6.7
