Key Differences

Advantages of GeForce RTX 3080
Advantages of Apple M4 GPU (8-core)

Specifications

Performance

TGP 320 W 15 W

Storage Details

Bus 320-bit 128-bit

Ports

DisplayPort 1.4a -

Other

Forza Horizon 5 17411410477 -
The Witcher 3 19415911761 -
Counter-Strike 2 26820514884 -
Far Cry 6 14913411669 -
Hogwarts Legacy 120997742 -
CoD: Modern Warfare III 15114710970 -
Ghost of Tsushima 107927544 -
Cyberpunk 2077 1321177838 -
Shadow of the Tomb Raider 21219715283 -
1080p High 167 -
1080p Ultra 140 -
1440p Ultra 108 -
4K Ultra 63 -
Margin of Error Low -
Time Spy 17663 -
Solar Bay 85879 -
Port Royal 11597 -
Fire Strike 42456 -
Wild Life Extreme 37890 -
Night Raid 132802 -
Background Blur 217.3 img/sec 57.4 img/sec
Face Detection 141.9 img/sec 41.3 img/sec
Horizon Detection 8.19 Gpixels/sec 1.21 Gpixels/sec
Edge Detection 11 Gpixels/sec 1.74 Gpixels/sec
Gaussian Blur 8.43 Gpixels/sec 1.12 Gpixels/sec
Feature Matching 1.29 Gpixels/sec 0.43 Gpixels/sec
Stereo Matching 780.7 Gpixels/sec 94.9 Gpixels/sec
Particle Physics 22538.5 FPS 3902.5 FPS
API OpenGL -
G2D Mark 1061 -
DirectX 11 207 FPS -
DirectX 12 100 FPS -
GPU Compute 14286 Ops/s -
Aztec Ruins Normal Tier 950.5 FPS -
Car Chase 809.5 FPS -
Manhattan 3.1.1 (1440p) 705.4 FPS -
T-Rex 3525.4 FPS -
Tessellation 6034.6 FPS -
ALU 2 6005.6 FPS -
Driver Overhead 2 283.8 FPS -
OS Windows -
Image Classification (SP) 9439 -
Image Segmentation (HP) 25471 -
Image Super Resolution (Q) 19892 -
Face Detection (HP) 46956 -
Pose Estimation (Q) 104704 -
Text Classification (SP) 2712 -
Machine Translation (HP) 4828 -
Object Detection (SP) 12153 -
Depth Estimation (Q) 36822 -
Style Transfer (SP) 246005 -
Framework ONNX -
Backend DirectML -
Vendor Nvidia Apple
Build Discrete Integrated
Released September 1, 2020 October 29, 2024
Launch price (MSRP) $699 -
Case Desktop Laptop
Purpose Gaming Professional
Segment High-end Mid-range
Architecture Ampere Apple M GPU
GPU Codename GA102 Custom
Rival Equivalent Radeon RX 6800 XT -
Base Clock 1440 MHz 500 MHz
Boost Clock 1710 MHz 1700 MHz
Shading Units 8704 1024
Texture Mapping Units (TMUs) 272 64
Render Output Units (ROPs) 96 32
Compute Units (Pipelines) 68 128
Tensor Cores 272 -
Ray-tracing Cores 68 -
L1 Cache 128KB per cluster -
L2 Cache 5MB shared -
Instructions Per Cycle 2 IPC 2 IPC
Pixel Fill Rate 164 GPixel/s 54 GPixel/s
Texture Fill Rate 465 GTexel/s 109 GTexel/s
Interface PCIe 4.0 x16 Custom
Manufacturing Samsung TSMC
Fabrication Process 8 nm 3 nm
Die Size 628 mm² -
Transistor Count 28 billion -
Transistor Density 44.59 MTr/mm² -
Memory Type GDDR6X System Shared
Memory Size 10 GB -
Memory Clock 1188 MHz 7500 MHz
Effective Memory Speed 19000 Mbps 15000 Mbps
ECC No No
DirectX 12 -
Vulkan 1.3 -
OpenGL 4.6 -
OpenCL 3.0 -
CUDA 8.6 -
Ray Tracing Yes Yes
DLSS DLSS 2 No
Max. Temperature - 100°C