GPU Wiki

GeForce RTX 5070 vs GeForce RTX 4070

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

Key Differences

  • GeForce RTX 5070 has more CUDA Cores (6144 vs 5888).
  • GeForce RTX 5070 has more Memory bandwidth (672 GB/s vs 504.2 GB/s).
  • Boost clock: GeForce RTX 5070 has 2,512 MHz; GeForce RTX 4070 has 2,475 MHz.
  • TDP / TBP / board power: GeForce RTX 5070 has 250 W; GeForce RTX 4070 has 200 W.
  • Architecture: GeForce RTX 5070 has Blackwell 2.0; GeForce RTX 4070 has Ada Lovelace.
  • Launch date: GeForce RTX 5070 has 2025-03-04; GeForce RTX 4070 has 2023-04-12.
Row order:
Muted cells indicate unavailable, not applicable, or not directly comparable specifications.
Spec GeForce RTX 5070 GeForce RTX 4070
Overview
Product name NVIDIA GeForce RTX 5070 NVIDIA GeForce RTX 4070
Architecture Blackwell 2.0 Ada Lovelace
Generation / family GeForce RTX 50 Series GeForce RTX 40 Series
GPU codename GB205 AD104
Launch date 2025-03-04 2023-04-12
Market segment Desktop in GeForce RTX 50 Series Desktop in GeForce RTX 40 Series
Board type / entry type Reference GPU Reference GPU
GPU
Process node TSMC 5 nm TSMC 5 nm
Die size 263 mm² 294 mm²
Transistor count 31.1 billion 35.8 billion
GPU chip GB205 AD104
SM / multiprocessor count 48 46
CUDA Cores 6144 5888
Tensor Cores 192 184
RT Cores 48 46
ROPs 80 64
TMUs 192 184
Clocks
Base / Core clock 2,325 MHz 1,920 MHz
Boost clock 2,512 MHz 2,475 MHz
Memory clock 1,750 MHz 1,313 MHz
Memory
Memory size 12 GB 12 GB
Memory type GDDR7 GDDR6X
Memory bus width 192-bit 192-bit
Memory bandwidth 672 GB/s 504.2 GB/s
Bus / Interface
Bus interface PCIe 5.0 x16 PCIe 4.0 x16
AGP / PCI / PCIe distinction PCIe PCIe
Power
TDP / TBP / board power 250 W 200 W
Recommended PSU 600 W 550 W
Power connectors 1x 16-pin 1x 16-pin
Slot width Dual-slot, 245 mm length, 40 mm width Dual-slot, 240 mm length, 40 mm width
Display / Media
Display outputs 1x HDMI 2.1b, 3x DisplayPort 2.1b 1x HDMI 2.1, 3x DisplayPort 1.4a
Features
DirectX support DirectX 12.2 DirectX 12.2
OpenGL support OpenGL 4.6 OpenGL 4.6
Vulkan support Vulkan 1.4 Vulkan 1.4
CUDA support 12.0 8.9
Shader Model 6.8 6.8
Ray tracing support Hardware RT units present Hardware RT units present
Performance / Benchmarks
FP32 throughput 30.87 TFLOPS 29.15 TFLOPS
FP16 throughput 30.87 TFLOPS 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.