GPU Comparison
GEFORCE
NVIDIA GeForce RTX 5090 Mobile
CORE STATE
GB203
VRAM
24 GB
CLOCK SPEED
1515 MHz
TDP
95 W
BUS WIDTH
256 bit
ARCHITECTURE
Blackwell 2.0
PROCESS
5 nm
LAUNCH DATE
2025
VS
GEFORCE
RTX A1000 Mobile
CORE STATE
GA107
VRAM
4 GB
CLOCK SPEED
1140 MHz
TDP
60 W
BUS WIDTH
128 bit
ARCHITECTURE
Ampere
PROCESS
8 nm
LAUNCH DATE
2022
PERFORMANCE BENCHMARKS
3dmark_3dmark_steel_nomad_dx12
geekbench_opencl
geekbench_vulkan
passmark_directx_10
passmark_directx_11
passmark_directx_12
passmark_directx_9
passmark_g2d
passmark_g3d
passmark_gpu_compute
DETAILED SPECIFICATIONS
SPECIFICATION
RTX 5090 Mobile
RTX A1000 Mobile
Core Specs
Shading Units
10,496
2,048
-80.5%
Shaders
10,496
2,048
-80.5%
TMUs
328
64
-80.5%
ROPs
112
32
-71.4%
SM Count
82
16
-80.5%
Clocks
Base Clock
990 MHz
630 MHz
Boost Clock
1515 MHz
1140 MHz
Memory Clock
1750 MHz
28 Gbps effective
1375 MHz
11 Gbps effective
Memory
Memory Size
24 GB
4 GB
VRAM (MB)
24,576
4,096
-83.3%
Memory Type
GDDR7
GDDR6
Memory Bus
256 bit
128 bit
Bandwidth
896.0 GB/s
176.0 GB/s
Cache
L1 Cache
128 KB (per SM)
128 KB (per SM)
L2 Cache
64 MB
2 MB
Performance
Pixel Rate
169.7 GPixel/s
36.48 GPixel/s
Texture Rate
496.9 GTexel/s
72.96 GTexel/s
FP32 (TFLOPS)
31.80 TFLOPS
4.669 TFLOPS
FP64 (TFLOPS)
496.9 GFLOPS (1:64)
72.96 GFLOPS (1:64)
FP16 (TFLOPS)
31.80 TFLOPS (1:1)
4.669 TFLOPS (1:1)
AI/RT
RT Cores
82
16
-80.5%
Tensor Cores
328
64
-80.5%
Power
TDP
95 W
60 W
TDP (W)
95
60
-36.8%
Power Connectors
None
None
Architecture
Architecture
Blackwell 2.0
Ampere
GPU Name
GB203
GA107
Generation
GeForce 50 Mobile
Ampere-MW
(Ax000)
Process Size
5 nm
8 nm
Transistors
45,600 million
8,700 million
Die Size
378 mm²
200 mm²
Foundry
TSMC
Samsung
Density
120.6M / 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
3.0
3.0
CUDA
12.0
8.6
Shader Model
6.8
6.8
Physical
Slot Width
IGP
IGP
Outputs
Portable Device Dependent
Portable Device Dependent
Bus Interface
PCIe 5.0 x16
PCIe 4.0 x8
Other
Production
Active
End-of-life
Predecessor
GeForce 40 Mobile
Quadro Turing-M
Successor
—
Ada-MW