Key Differences

Advantages of Radeon 840M
Advantages of GeForce RTX 3050 Laptop

Specifications

Performance

TGP 15-54 W (configurable) 35-95 W (configurable)

Storage Details

Bus - 128-bit

Ports

DisplayPort 2.1 1.4a

Other

Forza Horizon 5 301412 - 76453419
The Witcher 3 1012 - - 65513419
Counter-Strike 2 252013 - 112785624
Far Cry 6 241910 - 61534018
Hogwarts Legacy 12 - - - 38302312
CoD: Modern Warfare III 2218139 46392616
Ghost of Tsushima 139 - - 33252210
Cyberpunk 2077 1110 - - 3932219
Shadow of the Tomb Raider 181410 - 67573718
1080p High 18 60
1080p Ultra 14 46
1440p Ultra 9 33
4K Ultra - 16
Margin of Error High Low
Time Spy 1673 4881
Solar Bay 7110 21604
Port Royal 611 552
Fire Strike 5293 12555
Wild Life Extreme - 9431
Night Raid 22773 53542
Background Blur 31.8 img/sec 88.6 img/sec
Face Detection 16.8 img/sec 57.3 img/sec
Horizon Detection 0.46 Gpixels/sec 2.53 Gpixels/sec
Edge Detection 0.58 Gpixels/sec 3.33 Gpixels/sec
Gaussian Blur 0.42 Gpixels/sec 2.55 Gpixels/sec
Feature Matching 0.18 Gpixels/sec 0.76 Gpixels/sec
Stereo Matching 52.5 Gpixels/sec 256.5 Gpixels/sec
Particle Physics 2048.6 FPS 7465.5 FPS
API OpenGL OpenGL
G2D Mark - 489
DirectX 11 - 71 FPS
DirectX 12 - 46 FPS
GPU Compute - 3858 Ops/s
Aztec Ruins Normal Tier 139.4 FPS 360.1 FPS
Car Chase 124 FPS 318.7 FPS
Manhattan 3.1.1 (1440p) 98.1 FPS 261.5 FPS
T-Rex 441.1 FPS 1272.8 FPS
Tessellation 605.3 FPS 1731.1 FPS
ALU 2 635.4 FPS 1575.9 FPS
Driver Overhead 2 286.6 FPS 257.6 FPS
OS Windows Windows
Image Classification (SP) 1988 4349
Image Segmentation (HP) 2184 11416
Image Super Resolution (Q) 4788 8973
Face Detection (HP) 6857 18927
Pose Estimation (Q) 17396 34631
Text Classification (SP) 1628 2269
Machine Translation (HP) 2053 3539
Object Detection (SP) 1825 5046
Depth Estimation (Q) 8471 15772
Style Transfer (SP) 31032 75260
Framework ONNX ONNX
Backend DirectML DirectML
Vendor Amd Nvidia
Build Integrated Discrete
Released January 7, 2025 January 1, 2021
Case Laptop Laptop
Purpose Generic Gaming
Segment Entry-level Mid-range
Architecture RDNA 3.5 Ampere
GPU Codename Krackan Point GA107
Rival Equivalent Intel Arc 130T -
Base Clock - 712-1530 MHz (configurable)
Boost Clock 2900 MHz 1057-1740 MHz (configurable)
Shading Units 256 2048
Texture Mapping Units (TMUs) 16 64
Render Output Units (ROPs) 8 40
Compute Units (Pipelines) 4 16
Ray-tracing Cores 4 16
L1 Cache 128KB per cluster 128KB per cluster
L2 Cache 2MB shared 2MB shared
Instructions Per Cycle 4 IPC 2 IPC
Pixel Fill Rate 23 GPixel/s 42-70 GPixel/s
Texture Fill Rate 46 GTexel/s 68-111 GTexel/s
Interface PCIe 4.0 x16 PCIe 4.0 x16
Manufacturing TSMC Samsung
Fabrication Process 4 nm 8 nm
Die Size - 200 mm²
Transistor Count - 8.7 billion
Transistor Density - 43.5 MTr/mm²
Max. Temperature 100°C -
Memory Type System Shared GDDR6
DirectX 12 12
Vulkan 1.4 1.2
OpenGL 4.6 4.6
OpenCL 2.1 3.0
CUDA No 8.6
Ray Tracing Yes Yes
DLSS No DLSS 2
TGP / Version - 95W80W70W60W55W50W45W40W35W
Tensor Cores - 64
Memory Size - 4 GB
Memory Clock - 1500 MHz
Effective Memory Speed - 12000 Mbps
ECC - No