NVIDIA RTX PRO 6000 Blackwell Server vs NVIDIA RTX A4000
GPU · Specs Compare
Graphics Card
Release Date
Mar 2025
Apr 2021
Generation
Server Blackwell
Quadro Ampere
Type
Professional
Professional
Bus Interface
PCIe 5.0 x16
PCIe 4.0 x16
Clock Speeds
Base Clock
1590 MHz
735 MHz
Boost Clock
2617 MHz
1560 MHz
Memory Clock
1750 MHz
1750 MHz
Memory
Memory Size
96GB
16GB
Memory Type
GDDR7
GDDR6
Memory Bus
512bit
256bit
Bandwidth
1.79TB/s
448.0GB/s
Render Config
SM Count
188
48
Shading Units
24064
6144
TMUs
752
192
ROPs
192
96
Tensor Cores
752
192
RT Cores
188
48
L1 Cache
128 KB (per SM)
128 KB (per SM)
L2 Cache
128 MB
4 MB
Theoretical Performance
Pixel Rate
502.5 GPixel/s
149.8 GPixel/s
Texture Rate
1968.0 GTexel/s
299.5 GTexel/s
FP16 (half)
126.0 TFLOPS
19.17 TFLOPS
FP32 (float)
126.0 TFLOPS
19.17 TFLOPS
FP64 (double)
1.968 TFLOPS
299.5 GFLOPS
Graphics Processor
GPU Name
GB202
GA104
Architecture
Blackwell 2.0
Ampere
Foundry
TSMC
Samsung
Process Size
5 nm
8 nm
Transistors
92.2 billion
17.4 billion
Die Size
750 mm²
392 mm²
GPU Variant
—
GA104-875-A1
Board Design
TDP
600W
140W
Suggested PSU
1000 W
300 W
Outputs
4x DisplayPort 2.1b
4x DisplayPort 1.4a
Power Connectors
1x 16-pin
1x 6-pin
Graphics Features
DirectX
12 Ultimate (12_2)
12 Ultimate (12_2)
OpenGL
4.6
4.6
OpenCL
3.0
3.0
Vulkan
1.4
1.3
CUDA
12.0
8.6
Shader Model
6.9
6.7
Benchmark
3DMark Time Spy
—
11,079
3DMark Time Spy Extreme
—
5,367
OctaneBench
—
352
▲ Specs Compare
Data sourced from official specifications and benchmark tests.