NVIDIA RTX A6000 vs NVIDIA RTX 4000 SFF Ada Generation
We compared two Professional market GPUs: 48GB VRAM RTX A6000 and 16GB VRAM RTX 4000 SFF Ada Generation to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA RTX A6000 's Advantages
Released 1 years and 11 months late
Boost Clock has increased by 3% (1800MHz vs 1746MHz)
More VRAM (48GB vs 16GB)
6912 additional rendering cores
NVIDIA RTX 4000 SFF Ada Generation 's Advantages
Larger VRAM bandwidth (1.02TB/s vs 768.0GB/s)
Score
Benchmark
FP32 (float)
RTX A6000
+188%
38.71 TFLOPS
RTX 4000 SFF Ada Generation
13.41 TFLOPS
3DMark Time Spy
RTX A6000
+70%
17742
RTX 4000 SFF Ada Generation
10406
3DMark Time Spy Extreme
RTX A6000
+94%
9324
RTX 4000 SFF Ada Generation
4783
3DMark Speed Way
RTX A6000
+95%
4965
RTX 4000 SFF Ada Generation
2542
Blender
RTX A6000
+44%
5387
RTX 4000 SFF Ada Generation
3717
OctaneBench
RTX A6000
+35%
600
RTX 4000 SFF Ada Generation
443
Graphics Card
Oct 2020
Release Date
Nov 2018
Quadro Ampere
Generation
Radeon Instinct
Professional
Type
Professional
PCIe 4.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
1410 MHz
Base Clock
1200 MHz
1800 MHz
Boost Clock
1746 MHz
2000 MHz
Memory Clock
1000 MHz
Memory
48GB
Memory Size
16GB
GDDR6
Memory Type
HBM2
384bit
Memory Bus
4096bit
768.0GB/s
Bandwidth
1.02TB/s
Render Config
-
Compute Units
60
84
SM Count
48
10752
Shading Units
3840
336
TMUs
240
112
ROPs
64
336
Tensor Cores
192
84
RT Cores
48
128 KB (per SM)
L1 Cache
16 KB (per CU)
6 MB
L2 Cache
4 MB
-
-
-
Theoretical Performance
201.6 GPixel/s
Pixel Rate
111.7 GPixel/s
604.8 GTexel/s
Texture Rate
419.0 GTexel/s
38.71 TFLOPS
FP16 (half)
26.82 TFLOPS
38.71 TFLOPS
FP32 (float)
13.41 TFLOPS
604.8 GFLOPS
FP64 (double)
6.705 TFLOPS
Board Design
300W
TDP
300W
700 W
Suggested PSU
700 W
4x DisplayPort 1.4a
Outputs
1x mini-DisplayPort 1.4a
8-pin EPS
Power Connectors
2x 8-pin
Graphics Processor
GA102
GPU Name
Vega 20
-
GPU Variant
Vega 20 GLXT
Ampere
Architecture
GCN 5.1
Samsung
Foundry
TSMC
8 nm
Process Size
7 nm
28.3 billion
Transistors
13.23 billion
628 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
8.6
CUDA
8.9
6.7
Shader Model
6.7
