NVIDIA GeForce RTX 3050 vs NVIDIA GeForce RTX 3050 A 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 3050 offers more compute units (CUDA cores: 2048 vs 1792), a wider memory bus (128 bit vs 64 bit), and more RT units (16 vs 14). NVIDIA GeForce RTX 3050 A offers a smaller manufacturing process (5 nm vs 8 nm).
Performance score
0
Coming soon
0
Coming soon
Key specs
CUDA cores2048
CUDA cores1792
Boost1740 MHz
BoostN/A
VRAM4 GB
VRAM4 GB
Memory bus128 bit
Memory bus64 bit
TGP35–95 W
TGP35–95 W
MemoryGDDR6
MemoryGDDR6
General
SeriesRTX 30 Mobile
SeriesRTX 30 Mobile
GPU architectureAmpere
GPU architectureAda Lovelace
GPU chipGA107
GPU chipAD106
Chip variantGN20-P0-A1
FoundrySamsung
FoundryTSMC
Process node8 nm
Process node5 nm
Die size200 mm²
Die size190 mm²
Transistors8.7 billion
Transistors22.9 billion
InterfacePCIe 4.0 x8
InterfacePCIe 4.0 x8
Release dateMay 11, 2021
Release dateJuly 26, 2024
Cores and clocks
CUDA cores2048
CUDA cores1792
16× SM
14× SM
Boost clock (max)1740 MHz
Boost clock (max)N/A
Boost clock (min)1057 MHz
Memory
VRAM4 GB
VRAM4 GB
MemoryGDDR6
MemoryGDDR6
Memory bus128 bit
Memory bus64 bit
Memory speed12 Gb/s
Memory speedN/A
Bandwidth192 GB/s
BandwidthN/A
TGP
TGP range35 - 80 W
TGP range35 - 80 W
Dynamic Boost15 W
Dynamic Boost15 W
Cache
L2 cache2 MB
L2 cacheN/A
L1 cache128 KB
L1 cache128 KB
Units
TMUs64
TMUs56
ROPs32
ROPs32
RT cores16
RT cores14
Tensor cores64
Tensor cores56
SM blocks16
SM blocks14
AI
AI performanceN/A
AI performanceN/A