GPU Wiki
Compare 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.
Popular comparisons
| Spec | GeForce RTX 3050 8 GB GA107 |
|---|---|
| Overview | |
| Product name | NVIDIA GeForce RTX 3050 8 GB GA107 |
| Architecture | Ampere |
| Generation / family | GeForce RTX 30 Series |
| GPU codename | GA107 |
| Launch date | 2022-12-16 |
| Market segment | Desktop in GeForce RTX 30 Series |
| Board type / entry type | Reference GPU |
| GPU | |
| Process node | Samsung 8 nm |
| Die size | 200 mm² |
| Transistor count | 8.7 billion |
| GPU chip | GA107 |
| SM / multiprocessor count | 20 |
| CUDA Cores | 2560 |
| Tensor Cores | 80 |
| RT Cores | 20 |
| ROPs | 32 |
| TMUs | 80 |
| Clocks | |
| Base / Core clock | 1,552 MHz |
| Boost clock | 1,777 MHz |
| Memory clock | 1,750 MHz |
| Memory | |
| Memory size | 8 GB |
| Memory type | GDDR6 |
| Memory bus width | 128-bit |
| Memory bandwidth | 224 GB/s |
| Bus / Interface | |
| Bus interface | PCIe 4.0 x8 |
| AGP / PCI / PCIe distinction | PCIe |
| Power | |
| TDP / TBP / board power | 115 W |
| Recommended PSU | 300 W |
| Power connectors | 1x 6-pin |
| Slot width | Dual-slot, 242 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 | 8.6 |
| Shader Model | 6.8 |
| Ray tracing support | Hardware RT units present |
| Performance / Benchmarks | |
| FP32 throughput | 9.1 TFLOPS |
| FP16 throughput | 9.1 TFLOPS |
Overview
Product name
GeForce RTX 3050 8 GB GA107
NVIDIA GeForce RTX 3050 8 GB GA107
Architecture
GeForce RTX 3050 8 GB GA107
Ampere
Generation / family
GeForce RTX 3050 8 GB GA107
GeForce RTX 30 Series
GPU codename
GeForce RTX 3050 8 GB GA107
GA107
Launch date
GeForce RTX 3050 8 GB GA107
2022-12-16
Market segment
GeForce RTX 3050 8 GB GA107
Desktop in GeForce RTX 30 Series
Board type / entry type
GeForce RTX 3050 8 GB GA107
Reference GPU
GPU
Process node
GeForce RTX 3050 8 GB GA107
Samsung 8 nm
Die size
GeForce RTX 3050 8 GB GA107
200 mm²
Transistor count
GeForce RTX 3050 8 GB GA107
8.7 billion
GPU chip
GeForce RTX 3050 8 GB GA107
GA107
SM / multiprocessor count
GeForce RTX 3050 8 GB GA107
20
CUDA Cores
GeForce RTX 3050 8 GB GA107
2560
Tensor Cores
GeForce RTX 3050 8 GB GA107
80
RT Cores
GeForce RTX 3050 8 GB GA107
20
ROPs
GeForce RTX 3050 8 GB GA107
32
TMUs
GeForce RTX 3050 8 GB GA107
80
Clocks
Base / Core clock
GeForce RTX 3050 8 GB GA107
1,552 MHz
Boost clock
GeForce RTX 3050 8 GB GA107
1,777 MHz
Memory clock
GeForce RTX 3050 8 GB GA107
1,750 MHz
Memory
Memory size
GeForce RTX 3050 8 GB GA107
8 GB
Memory type
GeForce RTX 3050 8 GB GA107
GDDR6
Memory bus width
GeForce RTX 3050 8 GB GA107
128-bit
Memory bandwidth
GeForce RTX 3050 8 GB GA107
224 GB/s
Bus / Interface
Bus interface
GeForce RTX 3050 8 GB GA107
PCIe 4.0 x8
AGP / PCI / PCIe distinction
GeForce RTX 3050 8 GB GA107
PCIe
Power
TDP / TBP / board power
GeForce RTX 3050 8 GB GA107
115 W
Recommended PSU
GeForce RTX 3050 8 GB GA107
300 W
Power connectors
GeForce RTX 3050 8 GB GA107
1x 6-pin
Slot width
GeForce RTX 3050 8 GB GA107
Dual-slot, 242 mm length, 40 mm width
Display / Media
Display outputs
GeForce RTX 3050 8 GB GA107
1x HDMI 2.1, 3x DisplayPort 1.4a
Features
DirectX support
GeForce RTX 3050 8 GB GA107
DirectX 12.2
OpenGL support
GeForce RTX 3050 8 GB GA107
OpenGL 4.6
Vulkan support
GeForce RTX 3050 8 GB GA107
Vulkan 1.4
CUDA support
GeForce RTX 3050 8 GB GA107
8.6
Shader Model
GeForce RTX 3050 8 GB GA107
6.8
Ray tracing support
GeForce RTX 3050 8 GB GA107
Hardware RT units present
Performance / Benchmarks
FP32 throughput
GeForce RTX 3050 8 GB GA107
9.1 TFLOPS
FP16 throughput
GeForce RTX 3050 8 GB GA107
9.1 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.
