GPU Wiki

Compare NVIDIA GPUs

Select up to four GPU Wiki entries to compare matching specifications row by row. The comparison uses the site database and keeps generation-specific specs visibly separate.

Swap Clear
Row order:
Muted cells indicate unavailable, not applicable, or not directly comparable specifications.
Spec GeForce RTX 4070 AD103
Overview
Product name NVIDIA GeForce RTX 4070 AD103
Architecture Ada Lovelace
Generation / family GeForce RTX 40 Series
GPU codename AD103
Launch date 2024-03-01
Market segment Desktop in GeForce RTX 40 Series
Board type / entry type Reference GPU
GPU
Process node TSMC 5 nm
Die size 379 mm²
Transistor count 45.9 billion
GPU chip AD103
SM / multiprocessor count 46
CUDA Cores 5888
Tensor Cores 184
RT Cores 46
ROPs 64
TMUs 184
Clocks
Base / Core clock 1,920 MHz
Boost clock 2,475 MHz
Memory clock 1,313 MHz
Memory
Memory size 12 GB
Memory type GDDR6X
Memory bus width 192-bit
Memory bandwidth 504.2 GB/s
Bus / Interface
Bus interface PCIe 4.0 x16
AGP / PCI / PCIe distinction PCIe
Power
TDP / TBP / board power 200 W
Recommended PSU 550 W
Power connectors 1x 16-pin
Slot width Dual-slot, 240 mm length, 40 mm width
Display / Media
Display outputs 1x HDMI 2.1, 3x DisplayPort 1.4a
Features
DirectX support DirectX 12.2
OpenGL support OpenGL 4.6
Vulkan support Vulkan 1.4
CUDA support 8.9
Shader Model 6.8
Ray tracing support Hardware RT units present
Performance / Benchmarks
FP32 throughput 29.15 TFLOPS
FP16 throughput 29.15 TFLOPS

© 2026 NVIDIA Club. Independent GPU history, guides, and hardware knowledge.

NVIDIA Club is an independent enthusiast and technical knowledge site. It is not affiliated with, endorsed by, or sponsored by NVIDIA Corporation.