NVIDIA GeForce RTX 4060 vs NVIDIA GeForce RTX 4070 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 4060 offers a higher boost clock (2370 MHz vs 2175 MHz). NVIDIA GeForce RTX 4070 offers more compute units (CUDA cores: 4608 vs 3072), more RT units (36 vs 24), and higher AI performance (321 TOPS vs 233 TOPS).
Performance score
0
Coming soon
0
Coming soon
Key specs
CUDA cores3072
CUDA cores4608
Boost2370 MHz
Boost2175 MHz
VRAM8 GB
VRAM8 GB
Memory bus128 bit
Memory bus128 bit
TGP35–140 W
TGP35–140 W
MemoryGDDR6
MemoryGDDR6
General
SeriesRTX 40 Mobile
SeriesRTX 40 Mobile
GPU architectureAda Lovelace
GPU architectureAda Lovelace
GPU chipAD107
GPU chipAD106
Chip variantGN21-X4
Chip variantGN21-X6
FoundryTSMC
FoundryTSMC
Process node5 nm
Process node5 nm
Die size159 mm²
Die size190 mm²
Transistors18.9 billion
Transistors22.9 billion
InterfacePCIe 4.0 x8
InterfacePCIe 4.0 x8
Release dateJanuary 3, 2023
Release dateJanuary 3, 2023
Cores and clocks
CUDA cores3072
CUDA cores4608
24× SM
36× SM
Boost clock (max)2370 MHz
Boost clock (max)2175 MHz
Boost clock (min)1470 MHz
Boost clock (min)1230 MHz
Memory
VRAM8 GB
VRAM8 GB
MemoryGDDR6
MemoryGDDR6
Memory bus128 bit
Memory bus128 bit
Memory speed16 Gb/s
Memory speed16 Gb/s
Bandwidth256 GB/s
Bandwidth256 GB/s
TGP
TGP range35 - 115 W
TGP range35 - 115 W
Dynamic Boost25 W
Dynamic Boost25 W
Cache
L2 cache32 MB
L2 cache32 MB
L1 cache128 KB
L1 cache128 KB
Units
TMUs96
TMUs144
ROPs48
ROPs48
RT cores24
RT cores36
Tensor cores96
Tensor cores144
SM blocks24
SM blocks36
AI
AI performance233 TOPS
AI performance321 TOPS