GeForce RTX 3090 Ti vs Apple M3 Max GPU (40-core)
We performed a head-to-head comparison of the GeForce RTX 3090 Ti 24 GB with 84 pipelines and 10752 shaders against the 1 year and 7 months newer Apple M3 Max GPU (40-core) that utilizes 640 pipelines and 5120 shaders. Here you will find complete details about specs, efficiency, performance tests, and more.
Review
Gaming
Performance in DirectX, OpenCL, and Vulkan games
Workstation
Perf. in 3D modeling, video editing and rendering apps
AI/ML
Capabilities for machine learning and AI-related tasks
Energy Efficiency
Power consumption efficiency in different scenarios
NanoReview Final Score
Overall video card score
The "Energy Efficiency" metric has less impact on the NanoReview Score for desktop GPU.
Key differences
Reasons to consider the GeForce RTX 3090 Ti
- Performs significantly better (up to 2x) in 3DMark Steel Nomad Lite
- 2.8x higher maximum theoretical performance (40 vs 14.1 TFLOPS)
- Has 2.5x higher memory bandwidth: 1008 vs 409.6 GB/s
- Achieves 2.5x more points in the GeekBench 6 Compute test (232K vs 94K)
- Supports Nvidia DLSS 2 technology
- Has 2.1x more shading units (10752 vs 5120)
Reasons to consider the Apple M3 Max GPU (40-core)
- Manufactured using a more efficient 3 nm process technology
Gaming Performance
Frame rate comparison across popular AAA titles at different resolutionsGames
| Forza Horizon 5 | 200 136 126 99 |
- |
| The Witcher 3 | 214 185 130 71 |
- |
| Counter-Strike 2 | 286 213 154 85 |
- |
| Far Cry 6 | 160 151 133 83 |
- |
| Hogwarts Legacy | 141 116 93 52 |
- |
| CoD: Modern Warfare III | 186 174 139 90 |
- |
| Ghost of Tsushima | 129 105 89 57 |
- |
| Cyberpunk 2077 | 158 140 98 44 |
- |
| Shadow of the Tomb Raider | 254 237 183 101 |
- |
| 1080p High | 192 | - |
| 1080p Ultra | 162 | - |
| 1440p Ultra | 127 | - |
| 4K Ultra | 76 | - |
| Margin of Error | Low | Medium |
Benchmarks
Graphics cards’ performance in recent benchmarking apps3D Mark
Steel Nomad Lite Score
| Time Spy | 21855 | - |
| Solar Bay | 109239 | 49656 |
| Port Royal | 14890 | - |
| Fire Strike | 51935 | - |
| Wild Life Extreme | 48861 | 30893 |
| Night Raid | 156537 | - |
GeekBench 6 OpenCL
GB6 Compute Score
| Background Blur | 362.7 img/sec | 157.6 img/sec |
| Face Detection | 227.9 img/sec | 100.9 img/sec |
| Horizon Detection | 11.3 Gpixels/sec | 3.99 Gpixels/sec |
| Edge Detection | 15.9 Gpixels/sec | 6.04 Gpixels/sec |
| Gaussian Blur | 12.1 Gpixels/sec | 5 Gpixels/sec |
| Feature Matching | 1.56 Gpixels/sec | 0.84 Gpixels/sec |
| Stereo Matching | 1080 Gpixels/sec | 363.8 Gpixels/sec |
| Particle Physics | 31024.6 FPS | 12226.9 FPS |
| API | OpenCL | OpenCL |
Cinebench 2024 GPU
Cinebench 2024 GPU
Passmark Graphics
G3D Mark Score
| G2D Mark | 1226 | - |
| DirectX 11 | 238 FPS | - |
| DirectX 12 | 121 FPS | - |
| GPU Compute | 16494 Ops/s | - |
Blender
Blender GPU
Artificial Intelligence Tests
Performance in machine learning and artificial intelligence tasksGeekBench 6 ML
GB6 ML Single Precision
GB6 ML Half Precision
GB6 ML Quantized
| Image Classification (SP) | 10246 | 8685 |
| Image Segmentation (HP) | 22830 | 20739 |
| Image Super Resolution (Q) | 23532 | 22775 |
| Face Detection (HP) | 48657 | 37676 |
| Pose Estimation (Q) | 147241 | 91609 |
| Text Classification (SP) | 2917 | 2909 |
| Machine Translation (HP) | 4427 | 5274 |
| Object Detection (SP) | 13323 | 7480 |
| Depth Estimation (Q) | 40055 | 38212 |
| Style Transfer (SP) | 298683 | 190681 |
| Framework | ONNX | Core ML |
| Backend | DirectML | GPU |
Results were compared using different ML frameworks
Specifications
Technical specifications of GeForce RTX 3090 Ti and Apple M3 Max GPU (40-core)General
| Vendor | Nvidia | Apple |
| Build | Discrete | Integrated |
| Released | March 29, 2022 | October 31, 2023 |
| Launch price (MSRP) | $1999 | - |
| Case | Desktop | Laptop |
| Purpose | Gaming | Professional |
| Segment | High-end | High-end |
| Architecture | Ampere | Apple M GPU |
| GPU Codename | GA102 | - |
| Rival Equivalent | - | - GeForce RTX 4070 Laptop |
| Successor | - | - Apple M5 Max GPU (40-core) |
| Recommended CPU | - Intel Core i9 12900K or above | - Apple M3 Max or above |
| Used in CPUs | - | - Apple M3 Max |
Desktop GPU rating (#14th place)
Laptop GPU ranking (#20th place)
Graphics Processing Unit
| Base Clock | 1560 MHz | 500 MHz |
| Boost Clock | 1860 MHz | 1380 MHz |
| Shading Units | 10752 | 5120 |
| Texture Mapping Units (TMUs) | 336 | 320 |
| Render Output Units (ROPs) | 112 | 160 |
| Compute Units (Pipelines) | 84 | 640 |
| Tensor Cores | 336 | - |
| Ray-tracing Cores | 84 | - |
| L1 Cache | 128KB per cluster | - |
| L2 Cache | 6MB shared | - |
| Instructions Per Cycle | 2 IPC | 2 IPC |
Raw Performance
| Pixel Fill Rate | 208 GPixel/s | 221 GPixel/s |
| Texture Fill Rate | 625 GTexel/s | 442 GTexel/s |
FLOPS (FP32)
Physical
| Interface | PCIe 4.0 x16 | Custom |
| TGP | 450 W | 60 W |
| Manufacturing | Samsung | TSMC |
| Fabrication Process | 8 nm | 3 nm |
| Die Size | 628 mm² | - |
| Transistor Count | 28 billion | 56 billion |
| Transistor Density | 44.59 MTr/mm² | - |
| Max. Temperature | - | 100°C |
Memory
| Memory Type | GDDR6X | System Shared |
| Memory Size | 24 GB | - |
| Memory Clock | 1313 MHz | 6400 MHz |
| Effective Memory Speed | 21000 Mbps | 12800 Mbps |
| Bus | 384-bit | 512-bit |
| ECC | No | No |
Memory Bandwidth
API
| DirectX | 12 | - |
| Vulkan | 1.3 | - |
| OpenGL | 4.6 | - |
| OpenCL | 3.0 | - |
| CUDA | 8.6 | - |
| Ray Tracing | Yes | Yes |
| DLSS | DLSS 2 | No |
| DisplayPort | 1.4a | - |
Cast your vote
Total votes: 12