GPU Wiki

GeForce RTX 3070 vs GeForce GTX 1080 Ti

Swap Clear comparison
Edit GPUs
Add a third or fourth GPU

Key Differences

  • No game was measured on every one of these cards on one shared test system, so there is no speed comparison to make.
  • GTX 1080 Ti has the most memory: 11 GB against 8 GB.
  • GTX 1080 Ti has the most memory bandwidth: 484.4 GB/s against 448 GB/s.
  • RTX 3070 draws the least power: 220 W against 250 W.
Spec GeForce RTX 3070 GeForce GTX 1080 Ti
Overview
Product name NVIDIA GeForce RTX 3070 NVIDIA GeForce GTX 1080 Ti
Architecture Ampere Pascal
Generation / family GeForce RTX 30 Series GeForce GTX 10 Series
GPU codename GA104 GP102
Launch date 2020-10-29 2017-03-10
Market segment Desktop in GeForce RTX 30 Series Desktop, Flagship in GeForce GTX 10 Series
Board type / entry type Reference GPU Reference GPU
GPU
Process node Samsung 8 nm TSMC 16 nm
Die size 392 mm² 471 mm²
Transistor count 17.4 billion 11.8 billion
GPU chip GA104 GP102
SM / multiprocessor count 46 28
CUDA Cores 5888 3584
Tensor Cores 184 Unknown
RT Cores 46 Unknown
ROPs 96 88
TMUs 184 224
Clocks
Base / Core clock 1,500 MHz 1,481 MHz
Boost clock 1,725 MHz 1,582 MHz
Memory clock 1,750 MHz 1,376 MHz
Memory
Memory size 8 GB 11 GB
Memory type GDDR6 GDDR5X
Memory bus width 256-bit 352-bit
Memory bandwidth 448 GB/s 484.4 GB/s
Bus / Interface
Bus interface PCIe 4.0 x16 PCIe 3.0 x16
AGP / PCI / PCIe distinction PCIe PCIe
Power
TDP / TBP / board power 220 W 250 W
Recommended PSU 650 W 600 W
Power connectors 1x 12-pin 1x PCIe 6-pin + 1x PCIe 8-pin
Slot width Dual-slot, 242 mm length Dual-slot, 267 mm length, 40 mm width
Display / Media
Display outputs 1x HDMI 2.1, 3x DisplayPort 1.4a 1x HDMI 2.0, 3x DisplayPort 1.4a
Features
DirectX support DirectX 12.2 DirectX 12.1
OpenGL support OpenGL 4.6 OpenGL 4.6
Vulkan support Vulkan 1.4 Vulkan 1.4
CUDA support 8.6 6.1
Shader Model 6.8 6.8
Ray tracing support Hardware RT units present Unknown
Performance / Benchmarks
FP32 throughput 20.31 TFLOPS 11.34 TFLOPS
FP16 throughput 20.31 TFLOPS 0.18 TFLOPS
Muted cells indicate unavailable, not applicable, or not directly comparable specifications.

Frame rates compare runs of the same game at the same quality preset on one test system. DLAA counts as native resolution, because it applies anti-aliasing at full render resolution rather than upscaling; DLSS and FSR upscaling are never counted as native. Where a capture named ray tracing without a readable on or off value, it is read as on.