NVIDIA GeForce RTX 3070 vs NVIDIA GeForce RTX 3080 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 3080 offers more compute units (CUDA cores: 6144 vs 5120), a higher boost clock (1710 MHz vs 1620 MHz), more VRAM (16 GB vs 8 GB), and more RT units (48 vs 40).
Performance score
0
Coming soon
0
Coming soon
Key specs
CUDA cores5120
CUDA cores6144
Boost1620 MHz
Boost1710 MHz
VRAM8 GB
VRAM16 GB
Memory bus256 bit
Memory bus256 bit
TGP80–140 W
TGP80–175 W
MemoryGDDR6
MemoryGDDR6
General
SeriesRTX 30 Mobile
SeriesRTX 30 Mobile
GPU architectureAmpere
GPU architectureAmpere
GPU chipGA104
GPU chipGA104
Chip variantGN20-E5
Chip variantGN20-E7
FoundrySamsung
FoundrySamsung
Process node8 nm
Process node8 nm
Die size392 mm²
Die size392 mm²
Transistors17.4 billion
Transistors17.4 billion
InterfacePCIe 4.0 x16
InterfacePCIe 4.0 x16
Release dateJanuary 12, 2021
Release dateJanuary 12, 2021
Cores and clocks
CUDA cores5120
CUDA cores6144
40× SM
48× SM
Boost clock (max)1620 MHz
Boost clock (max)1710 MHz
Boost clock (min)1290 MHz
Boost clock (min)1245 MHz
Memory
VRAM8 GB
VRAM16 GB
MemoryGDDR6
MemoryGDDR6
Memory bus256 bit
Memory bus256 bit
Memory speed14 Gb/s
Memory speed14 Gb/s
Bandwidth448 GB/s
Bandwidth448 GB/s
TGP
TGP range80 - 125 W
TGP range80 - 150 W
Dynamic Boost15 W
Dynamic Boost25 W
Cache
L2 cache4 MB
L2 cache4 MB
L1 cache128 KB
L1 cache128 KB
Units
TMUs160
TMUs192
ROPs80
ROPs96
RT cores40
RT cores48
Tensor cores160
Tensor cores192
SM blocks40
SM blocks48
AI
AI performanceN/A
AI performanceN/A