NVIDIA GeForce RTX 4050 Laptop 115W vs AMD Radeon M625

NVIDIA GeForce RTX 4050 Laptop 115W
AMD Radeon M625
2560 Shaders
6GB GDDR6
2370MHz
384 Shaders
2GB GDDR5
1024MHz
Peak AI Performance
388.3 TOPS
INT4 Tensor Sparse
Peak AI Performance
790 GFLOPS
FP32
FP32
12.13 TFLOPS
FP32
790 GFLOPS
FP16
12.13 TFLOPS
-
-
Form Factor
Soldered
-
Form Factor
Soldered
-
TDP
115W
TDP
50W
-
-
-
-
-
-
-
-
-
-
GB6 OpenCL N/A
0%
GB6 OpenCL N/A
0%
GB6 Metal N/A
0%
GB6 Metal N/A
0%
GB6 Vulkan N/A
0%
GB6 Vulkan N/A
0%
GB5 OpenCL N/A
0%
GB5 OpenCL N/A
0%
GB5 CUDA N/A
0%
GB5 CUDA N/A
0%
GB5 Metal N/A
0%
GB5 Metal N/A
0%
GB5 Vulkan N/A
0%
GB5 Vulkan N/A
0%
OCT 2020.1 N/A
0%
OCT 2020.1 N/A
0%
OCT Metal N/A
0%
OCT Metal N/A
0%
Manufacturer
NVIDIA
Manufacturer
AMD
Chip Designer
NVIDIA
Chip Designer
AMD
Architecture
Ada Lovelace
Architecture
GCN 3
Family
GeForce 40
Family
Radeon RX 600
Codename
NV187
AD107
Variant
GN21-X2
Codename
Topaz
Polaris 24
Variant
Polaris 24 XTM
Market Segment
Laptop
Market Segment
Laptop
Release Date
2/22/2023
Release Date
8/13/2019
Foundry
TSMC
-
Foundry
TSMC
-
Fabrication Node
4N
-
Fabrication Node
28nm
-
Die Size
159 mm²
-
Die Size
125 mm²
-
Transistor Count
18.9 Billion
-
Transistor Count
1.6 Billion
-
Transistor Density
118.87M/mm²
-
Transistor Density
12.40M/mm²
-
Form
Soldered
Form
Soldered
Shading Units
2560 Shaders
-
Shading Units
384 Shaders
-
Texture Mapping Units
80 TMUs
Texture Mapping Units
24 TMUs
Render Output Units
32 ROPs
Render Output Units
8 ROPs
Tensor Cores
80 T-Cores
-
-
Ray-Tracing Cores
20 RT-Cores
-
-
Streaming Multiprocessors
20 SMs
-
-
-
-
Compute Units
6 CUs
-
-
-
-
Graphics Processing Clusters
2 GPCs
-
-
-
-
2370MHz Base
2370MHz
-
-
730MHz Base
1024MHz
Peak AI Performance
388.3 TOPS
INT4 Tensor Sparse
Peak AI Performance
790 GFLOPS
FP32
-
-
-
-
-
-
FP8
-
97.08 TFLOPS Tensor (FP16 Accumulate)
194.15 TFLOPS Tensor (FP16 Accumulate) Sparse
48.54 TFLOPS Tensor (FP32 Accumulate)
97.08 TFLOPS Tensor (FP32 Accumulate) Sparse
-
-
-
-
-
-
FP16
12.13 TFLOPS
48.54 TFLOPS Tensor (FP16 Accumulate)
97.08 TFLOPS Tensor (FP16 Accumulate) Sparse
24.27 TFLOPS Tensor (FP32 Accumulate)
48.54 TFLOPS Tensor (FP32 Accumulate) Sparse
-
-
-
-
-
-
FP32
12.13 TFLOPS
-
-
FP32
790 GFLOPS
-
-
FP64
190 GFLOPS
-
FP64
50 GFLOPS
-
BF16
12.13 TFLOPS
24.27 TFLOPS Tensor
48.54 TFLOPS Tensor Sparse
-
-
-
-
TF32
12.13 TFLOPS Tensor
24.27 TFLOPS Tensor Sparse
-
-
-
INT4
194.15 TOPS Tensor
388.3 TOPS Tensor Sparse
-
-
-
INT8
-
97.08 TOPS Tensor
194.15 TOPS Tensor Sparse
-
-
-
-
INT32
6.07 TOPS
-
-
Ray Tracing
28 TOPS
-
-
Pixel Fillrate
75.84 GPixel/s
Pixel Fillrate
8.192 GPixel/s
-
-
-
-
Texture Fillrate
189.6 GTexel/s
Texture Fillrate
24.576 GTexel/s
-
-
-
-
L1
64KB/SM Tex
128KB/SM
-
-
L1
-
-
16KB/CU
-
L2
12MB Shared
L2
256KB Shared
-
-
-
-
-
-
6GB
GDDR6
-
2GB
GDDR5
-
Bus Width
96Bit
Bus Width
64Bit
Clock
2000MHz
Transfer Rate
16GT/s
Bandwidth
192GB/s
Clock
1125MHz
Transfer Rate
4.5GT/s
Bandwidth
36GB/s
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
TDP
115W
TDP
50W
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
No Ports
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
No Ports
Max Resolution
7680x4320
Max Resolution
4096x2160
Max Resolution Refresh Rate
60Hz
Max Resolution Refresh Rate
60Hz
Variable Refresh Rate
G-Sync
FreeSync
-
Variable Refresh Rate
-
FreeSync
-
Display Stream Compression (DSC)
Supported
Display Stream Compression (DSC)
Not Supported
Multi Monitor Support
4
Multi Monitor Support
3
Content Protection
HDCP 2.3
Content Protection
HDCP 1.4
Model
NVENC 8
No Encoders
-
Codec
-
-
-
-
-
-
-
-
AVC (H.264)
HEVC (H.265)
-
AV1
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Model
NVDEC 5
No Decoders
Codec
MPEG-1
MPEG-2
MPEG-4
-
VC-1
VP8
VP9
-
AVC (H.264)
HEVC (H.265)
-
AV1
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Direct X
12
Direct 3D
12_3
Direct X
12
Direct 3D
12_0
OpenGL
4.6
OpenCL
3.0
Vulkan
1.3
OpenGL
4.6
OpenCL
2.1
Vulkan
1.2
Shader Model
6.7
CUDA
8.9
-
-
PureVideo HD
VP12
VDPAU
Feature Set L
Shader Model
6.5
-
-
GFX
8
-
-
-
-
Not a Card
-
-
-
Not a Card
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
PCIe Version
4.0
PCIe Lanes
16
-
-
PCIe Version
3.0
PCIe Lanes
8
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Change Comparison