NVIDIA Quadro RTX 3000 vs NVIDIA Quadro RTX 6000 graphics comparison: performance score, cores and clock speeds, VRAM, TGP, cache, and RT and AI units. The better value in each row is highlighted in green.
Summary
NVIDIA Quadro RTX 6000 offers more compute units (CUDA cores: 4608 vs 1920), a higher boost clock (1455 MHz vs 1380 MHz), more VRAM (24 GB vs 6 GB), a wider memory bus (384 bit vs 192 bit), and higher memory bandwidth (672 GB/s vs 336 GB/s).
Performance score
0
Coming soon
0
Coming soon
Key specs
CUDA cores1920
CUDA cores4608
Boost1380 MHz
Boost1455 MHz
VRAM6 GB
VRAM24 GB
Memory bus192 bit
Memory bus384 bit
TGP80 W
TGP200 W
MemoryGDDR6
MemoryGDDR6
General
SeriesQuadro Turing Mobile
SeriesQuadro Turing Mobile
GPU architectureTuring
GPU architectureTuring
GPU chipTU106
GPU chipTU102
Chip variantN19E-Q1-KA-K1
FoundryTSMC
FoundryTSMC
Process node12 nm
Process node12 nm
Die size445 mm²
Die size754 mm²
Transistors10.8 billion
Transistors18.6 billion
InterfacePCIe 3.0 x16
InterfacePCIe 3.0 x16
Release dateMay 27, 2019
Release dateSeptember 4, 2019
Cores and clocks
CUDA cores1920
CUDA cores4608
30× SM
72× SM
Boost clock1380 MHz
Boost clock1455 MHz
Memory
VRAM6 GB
VRAM24 GB
MemoryGDDR6
MemoryGDDR6
Memory bus192 bit
Memory bus384 bit
Memory speed14 Gb/s
Memory speed14 Gb/s
Bandwidth336 GB/s
Bandwidth672 GB/s
TGP
TGP range80 W
TGP range200 W
Cache
L2 cache3 MB
L2 cache6 MB
L1 cache64 KB
L1 cache64 KB
Units
TMUs120
TMUs288
ROPs48
ROPs96
RT cores30
RT cores72
Tensor cores240
Tensor cores576
SM blocks30
SM blocks72
AI
AI performanceN/A
AI performanceN/A