NVIDIA RTX PRO 2000 vs NVIDIA RTX PRO 3000 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 RTX PRO 3000 offers more compute units (CUDA cores: 5888 vs 3328), more VRAM (12 GB vs 8 GB), a wider memory bus (192 bit vs 128 bit), higher memory bandwidth (672 GB/s vs 384 GB/s), and more L2 cache (48 MB vs 32 MB).
Performance score
0
Coming soon
0
Coming soon
Key specs
CUDA cores3328
CUDA cores5888
BoostN/A
BoostN/A
VRAM8 GB
VRAM12 GB
Memory bus128 bit
Memory bus192 bit
TGP45–115 W
TGP60–140 W
MemoryGDDR7
MemoryGDDR7
General
SeriesRTX PRO Blackwell Mobile
SeriesRTX PRO Blackwell Mobile
GPU architectureBlackwell
GPU architectureBlackwell
GPU chipGB206
GPU chipGB205
FoundryTSMC
FoundryTSMC
Process node5 nm
Process node5 nm
Die size181 mm²
Die size263 mm²
Transistors21.9 billion
Transistors31.1 billion
InterfacePCIe 5.0 x8
InterfacePCIe 5.0 x16
Release dateMarch 18, 2025
Release dateMarch 18, 2025
Cores and clocks
CUDA cores3328
CUDA cores5888
26× SM
46× SM
Boost clock (max)N/A
Boost clock (max)N/A
Memory
VRAM8 GB
VRAM12 GB
MemoryGDDR7
MemoryGDDR7
Memory bus128 bit
Memory bus192 bit
Memory speed24 Gb/s
Memory speed28 Gb/s
Bandwidth384 GB/s
Bandwidth672 GB/s
TGP
TGP range45 - 115 W
TGP range60 - 140 W
Cache
L2 cache32 MB
L2 cache48 MB
L1 cache128 KB
L1 cache128 KB
Units
TMUs104
TMUs184
ROPs48
ROPs80
RT cores26
RT cores46
Tensor cores104
Tensor cores184
SM blocks26
SM blocks46
AI
AI performance572 TOPS
AI performance992 TOPS