NVIDIA RTX 4000 SFF Ada Generation vs NVIDIA RTX PRO 6000 Blackwell Server

GPU Specs Compare

Graphics Card

Release Date
Nov 2018
Mar 2025
Generation
Radeon Instinct
Server Blackwell
Type
Professional
Professional
Bus Interface
PCIe 4.0 x16
PCIe 5.0 x16

Clock Speeds

Base Clock
1200 MHz
1590 MHz
Boost Clock
1746 MHz
2617 MHz
Memory Clock
1000 MHz
1750 MHz

Memory

Memory Size
16GB
96GB
Memory Type
HBM2
GDDR7
Memory Bus
4096bit
512bit
Bandwidth
1.02TB/s
1.79TB/s

Render Config

SM Count
48
188
Compute Units
60
-
Shading Units
3840
24064
TMUs
240
752
ROPs
64
192
Tensor Cores
192
752
RT Cores
48
188
L1 Cache
16 KB (per CU)
128 KB (per SM)
L2 Cache
4 MB
128 MB

Theoretical Performance

Pixel Rate
111.7 GPixel/s
502.5 GPixel/s
Texture Rate
419.0 GTexel/s
1968.0 GTexel/s
FP16 (half)
26.82 TFLOPS
126.0 TFLOPS
FP32 (float)
13.41 TFLOPS
126.0 TFLOPS
FP64 (double)
6.705 TFLOPS
1.968 TFLOPS

Graphics Processor

GPU Name
Vega 20
GB202
GPU Variant
Vega 20 GLXT
-
Architecture
GCN 5.1
Blackwell 2.0
Foundry
TSMC
TSMC
Process Size
7 nm
5 nm
Transistors
13.23 billion
92.2 billion
Die Size
331 mm²
750 mm²

Board Design

TDP
300W
600W
Suggested PSU
700 W
1000 W
Outputs
1x mini-DisplayPort 1.4a
4x DisplayPort 2.1b
Power Connectors
2x 8-pin
1x 16-pin

Graphics Features

DirectX
12 (12_1)
12 Ultimate (12_2)
OpenGL
4.6
4.6
OpenCL
2.1
3.0
Vulkan
1.3
1.4
CUDA
8.9
12.0
Shader Model
6.7
6.9