NVIDIA GeForce RTX 4080 vs NVIDIA GeForce RTX 4090 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 GeForce RTX 4080 offers a higher boost clock (2280 MHz vs 2040 MHz). NVIDIA GeForce RTX 4090 offers more compute units (CUDA cores: 9728 vs 7424), more VRAM (16 GB vs 12 GB), a wider memory bus (256 bit vs 192 bit), higher memory bandwidth (576 GB/s vs 432 GB/s), and more L2 cache (64 MB vs 48 MB).
Performance score
0
Coming soon
0
Coming soon
Key specs
CUDA cores7424
CUDA cores9728
Boost2280 MHz
Boost2040 MHz
VRAM12 GB
VRAM16 GB
Memory bus192 bit
Memory bus256 bit
TGP60–175 W
TGP80–175 W
MemoryGDDR6
MemoryGDDR6
General
SeriesRTX 40 Mobile
SeriesRTX 40 Mobile
GPU architectureAda Lovelace
GPU architectureAda Lovelace
GPU chipAD104
GPU chipAD103
Chip variantGN21-X9
Chip variantGN21-X11
FoundryTSMC
FoundryTSMC
Process node5 nm
Process node5 nm
Die size295 mm²
Die size379 mm²
Transistors35.8 billion
Transistors45.9 billion
InterfacePCIe 4.0 x16
InterfacePCIe 4.0 x16
Release dateJanuary 3, 2023
Release dateJanuary 3, 2023
Cores and clocks
CUDA cores7424
CUDA cores9728
58× SM
76× SM
Boost clock (max)2280 MHz
Boost clock (max)2040 MHz
Boost clock (min)1350 MHz
Boost clock (min)1455 MHz
Memory
VRAM12 GB
VRAM16 GB
MemoryGDDR6
MemoryGDDR6
Memory bus192 bit
Memory bus256 bit
Memory speed18 Gb/s
Memory speed18 Gb/s
Bandwidth432 GB/s
Bandwidth576 GB/s
TGP
TGP range60 - 150 W
TGP range80 - 150 W
Dynamic Boost25 W
Dynamic Boost25 W
Cache
L2 cache48 MB
L2 cache64 MB
L1 cache128 KB
L1 cache128 KB
Units
TMUs232
TMUs304
ROPs80
ROPs112
RT cores58
RT cores76
Tensor cores232
Tensor cores304
SM blocks58
SM blocks76
AI
AI performance542 TOPS
AI performance686 TOPS