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.
Row order:
Muted cells indicate unavailable, not applicable, or not directly comparable specifications.
| Spec | GeForce RTX 2050 Max-Q |
|---|---|
| Overview | |
| Product name | NVIDIA GeForce RTX 2050 Max-Q |
| Architecture | Ampere |
| Generation / family | GeForce RTX 20 Series |
| GPU codename | GA107 |
| Launch date | 2021-12-17 |
| Market segment | Laptop in GeForce RTX 20 Series |
| Board type / entry type | Laptop GPU |
| GPU | |
| Process node | Samsung 8 nm |
| Die size | 200 mm² |
| Transistor count | 8.7 billion |
| GPU chip | GA107 |
| SM / multiprocessor count | 16 |
| CUDA Cores | 2048 |
| Tensor Cores | 64 |
| RT Cores | 32 |
| ROPs | 32 |
| TMUs | 64 |
| Clocks | |
| Base / Core clock | 832 MHz |
| Boost clock | 1,155 MHz |
| Memory clock | 1,475 MHz |
| Memory | |
| Memory size | 4 GB |
| Memory type | GDDR6 |
| Memory bus width | 64-bit |
| Memory bandwidth | 94.4 GB/s |
| Bus / Interface | |
| Bus interface | PCIe 3.0 x8 |
| AGP / PCI / PCIe distinction | PCIe |
| Power | |
| TDP / TBP / board power | 30 W |
| Power connectors | None |
| Display / Media | |
| Display outputs | 1x DVI, 1x HDMI 2.1, 2x 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 | 4.73 TFLOPS |
| FP16 throughput | 9.46 TFLOPS |
Overview
Product name
GeForce RTX 2050 Max-Q
NVIDIA GeForce RTX 2050 Max-Q
Architecture
GeForce RTX 2050 Max-Q
Ampere
Generation / family
GeForce RTX 2050 Max-Q
GeForce RTX 20 Series
GPU codename
GeForce RTX 2050 Max-Q
GA107
Launch date
GeForce RTX 2050 Max-Q
2021-12-17
Market segment
GeForce RTX 2050 Max-Q
Laptop in GeForce RTX 20 Series
Board type / entry type
GeForce RTX 2050 Max-Q
Laptop GPU
GPU
Process node
GeForce RTX 2050 Max-Q
Samsung 8 nm
Die size
GeForce RTX 2050 Max-Q
200 mm²
Transistor count
GeForce RTX 2050 Max-Q
8.7 billion
GPU chip
GeForce RTX 2050 Max-Q
GA107
SM / multiprocessor count
GeForce RTX 2050 Max-Q
16
CUDA Cores
GeForce RTX 2050 Max-Q
2048
Tensor Cores
GeForce RTX 2050 Max-Q
64
RT Cores
GeForce RTX 2050 Max-Q
32
ROPs
GeForce RTX 2050 Max-Q
32
TMUs
GeForce RTX 2050 Max-Q
64
Clocks
Base / Core clock
GeForce RTX 2050 Max-Q
832 MHz
Boost clock
GeForce RTX 2050 Max-Q
1,155 MHz
Memory clock
GeForce RTX 2050 Max-Q
1,475 MHz
Memory
Memory size
GeForce RTX 2050 Max-Q
4 GB
Memory type
GeForce RTX 2050 Max-Q
GDDR6
Memory bus width
GeForce RTX 2050 Max-Q
64-bit
Memory bandwidth
GeForce RTX 2050 Max-Q
94.4 GB/s
Bus / Interface
Bus interface
GeForce RTX 2050 Max-Q
PCIe 3.0 x8
AGP / PCI / PCIe distinction
GeForce RTX 2050 Max-Q
PCIe
Power
TDP / TBP / board power
GeForce RTX 2050 Max-Q
30 W
Power connectors
GeForce RTX 2050 Max-Q
None
Display / Media
Display outputs
GeForce RTX 2050 Max-Q
1x DVI, 1x HDMI 2.1, 2x DisplayPort 1.4a
Features
DirectX support
GeForce RTX 2050 Max-Q
DirectX 12.2
OpenGL support
GeForce RTX 2050 Max-Q
OpenGL 4.6
Vulkan support
GeForce RTX 2050 Max-Q
Vulkan 1.4
CUDA support
GeForce RTX 2050 Max-Q
8.6
Shader Model
GeForce RTX 2050 Max-Q
6.8
Ray tracing support
GeForce RTX 2050 Max-Q
Hardware RT units present
Performance / Benchmarks
FP32 throughput
GeForce RTX 2050 Max-Q
4.73 TFLOPS
FP16 throughput
GeForce RTX 2050 Max-Q
9.46 TFLOPS