GPU Comparison
RADEON
AMD Steam Deck GPU
CORE STATE
Van Gogh
VRAM
16 GB
CLOCK SPEED
1600 MHz
TDP
15 W
BUS WIDTH
128 bit
ARCHITECTURE
RDNA 2.0
PROCESS
7 nm
LAUNCH DATE
2022
VS
GEFORCE
GeForce RTX 2050 Mobile
CORE STATE
GA107
VRAM
4 GB
CLOCK SPEED
1245 MHz
TDP
30 W
BUS WIDTH
64 bit
ARCHITECTURE
Ampere
PROCESS
8 nm
LAUNCH DATE
2021
PERFORMANCE BENCHMARKS
3dmark_3dmark_steel_nomad_dx12
DETAILED SPECIFICATIONS
SPECIFICATION
Steam Deck GPU
RTX 2050 Mobile
Core Specs
Shading Units
512
2,048
+300.0%
Shaders
512
2,048
+300.0%
TMUs
32
64
+100.0%
ROPs
16
32
+100.0%
Compute Units
8
—
SM Count
—
16
Clocks
Base Clock
1000 MHz
735 MHz
Boost Clock
1600 MHz
1245 MHz
Memory Clock
1375 MHz
11 Gbps effective
1750 MHz
14 Gbps effective
Memory
Memory Size
16 GB
4 GB
VRAM (MB)
16,384
4,096
-75.0%
Memory Type
LPDDR5
GDDR6
Memory Bus
128 bit
64 bit
Bandwidth
176.0 GB/s
112.0 GB/s
Cache
L1 Cache
128 KB per Array
64 KB (per SM)
L2 Cache
1024 KB
2 MB
L0 Cache
32 KB per WGP
—
Performance
Pixel Rate
25.60 GPixel/s
39.84 GPixel/s
Texture Rate
51.20 GTexel/s
79.68 GTexel/s
FP32 (TFLOPS)
1.638 TFLOPS
5.100 TFLOPS
FP64 (TFLOPS)
102.4 GFLOPS (1:16)
159.4 GFLOPS (1:32)
FP16 (TFLOPS)
3.277 TFLOPS (2:1)
10.20 TFLOPS (2:1)
AI/RT
RT Cores
8
32
+300.0%
Tensor Cores
—
64
Power
TDP
15 W
30 W
TDP (W)
15
30
+100.0%
Power Connectors
—
None
Architecture
Architecture
RDNA 2.0
Ampere
GPU Name
Van Gogh
GA107
Generation
Console GPU
(Valve)
GeForce 20 Mobile
Process Size
7 nm
8 nm
Transistors
2,400 million
8,700 million
Die Size
163 mm²
200 mm²
Foundry
TSMC
Samsung
Density
14.7M / mm²
43.5M / mm²
API Support
DirectX
12 Ultimate (12_2)
12 Ultimate (12_2)
OpenGL
4.6
4.6
Vulkan
1.4
1.4
OpenCL
2.0
3.0
CUDA
—
8.6
Shader Model
6.8
6.8
Physical
Length
298 mm
11.7 inches
229 mm
9 inches
Height
117 mm
4.6 inches
113 mm
4.4 inches
Outputs
1x USB Type-C
1x DVI1x HDMI 2.12x DisplayPort 1.4a
Bus Interface
—
PCIe 3.0 x8
Other
Production
Active
End-of-life
Predecessor
—
GeForce 10 Mobile
Successor
—
GeForce 30 Mobile