NVIDIA GeForce RTX 4050 Max-Q vs AMD Radeon R7 M445

NVIDIA GeForce RTX 4050 Max-Q
AMD Radeon R7 M445
2560 Shaders
6GB GDDR6
1605MHz
320 Shaders
4GB GDDR5
920MHz
Peak AI Performance
262.96 TOPS
INT4 Tensor Sparse
Peak AI Performance
590 GFLOPS
FP32
FP32
8.22 TFLOPS
FP32
590 GFLOPS
FP16
8.22 TFLOPS
-
-
Form Factor
Soldered
-
Form Factor
Soldered
-
TDP
35W
TDP
20W
-
-
-
-
-
-
-
-
-
-
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 R 400
Codename
NV187
AD107
Variant
GN21-X2
Codename
Topaz
-
Variant
Meso Pro
Market Segment
Laptop
Market Segment
Laptop
Release Date
2/22/2023
Release Date
5/15/2016
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
320 Shaders
-
Texture Mapping Units
80 TMUs
Texture Mapping Units
20 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
5 CUs
-
-
-
-
Graphics Processing Clusters
2 GPCs
-
-
-
-
1140MHz Base
1605MHz
-
-
780MHz Base
920MHz
Peak AI Performance
262.96 TOPS
INT4 Tensor Sparse
Peak AI Performance
590 GFLOPS
FP32
-
-
-
-
-
-
FP8
-
65.74 TFLOPS Tensor (FP16 Accumulate)
131.48 TFLOPS Tensor (FP16 Accumulate) Sparse
32.87 TFLOPS Tensor (FP32 Accumulate)
65.74 TFLOPS Tensor (FP32 Accumulate) Sparse
-
-
-
-
-
-
FP16
8.22 TFLOPS
32.87 TFLOPS Tensor (FP16 Accumulate)
65.74 TFLOPS Tensor (FP16 Accumulate) Sparse
16.43 TFLOPS Tensor (FP32 Accumulate)
32.87 TFLOPS Tensor (FP32 Accumulate) Sparse
-
-
-
-
-
-
FP32
8.22 TFLOPS
-
-
FP32
590 GFLOPS
-
-
FP64
130 GFLOPS
-
FP64
40 GFLOPS
-
BF16
8.22 TFLOPS
16.43 TFLOPS Tensor
32.87 TFLOPS Tensor Sparse
-
-
-
-
TF32
8.22 TFLOPS Tensor
16.44 TFLOPS Tensor Sparse
-
-
-
INT4
131.48 TOPS Tensor
262.96 TOPS Tensor Sparse
-
-
-
INT8
-
65.74 TOPS Tensor
131.48 TOPS Tensor Sparse
-
-
-
-
INT32
4.11 TOPS
-
-
Ray Tracing
19 TOPS
-
-
Pixel Fillrate
51.36 GPixel/s
Pixel Fillrate
7.36 GPixel/s
-
-
-
-
Texture Fillrate
128.4 GTexel/s
Texture Fillrate
18.4 GTexel/s
-
-
-
-
L1
64KB/SM Tex
128KB/SM
-
-
L1
-
-
16KB/CU
-
L2
12MB Shared
L2
256KB Shared
-
-
-
-
-
-
6GB
GDDR6
-
4GB
GDDR5
-
Bus Width
96Bit
Bus Width
64Bit
Clock
2000MHz
Transfer Rate
16GT/s
Bandwidth
192GB/s
Clock
1000MHz
Transfer Rate
4GT/s
Bandwidth
32GB/s
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
TDP
35W
TDP
20W
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
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