Apple M1 Ultra 48-core vs NVIDIA RTX A3000 Mobile
Comparative analysis of Apple M1 Ultra 48-core and NVIDIA RTX A3000 Mobile videocards for all known characteristics in the following categories: Essentials, Technical info, Memory, Video outputs and ports, Compatibility, dimensions and requirements, API support. Benchmark videocards performance analysis: Geekbench - OpenCL, PassMark - G2D Mark, PassMark - G3D Mark, GFXBench 4.0 - Car Chase Offscreen (Frames), GFXBench 4.0 - Car Chase Offscreen (Fps), GFXBench 4.0 - Manhattan (Frames), GFXBench 4.0 - Manhattan (Fps), GFXBench 4.0 - T-Rex (Frames), GFXBench 4.0 - T-Rex (Fps).
Differences
Reasons to consider the Apple M1 Ultra 48-core
- Around 20% higher core clock speed: 1296 MHz vs 1080 MHz
- A newer manufacturing process allows for a more powerful, yet cooler running videocard: 5 nm vs 8 nm
- Around 8% lower typical power consumption: 120 Watt vs 130 Watt
- Around 20% better performance in Geekbench - OpenCL: 95143 vs 78981
| Specifications (specs) | |
| Core clock speed | 1296 MHz vs 1080 MHz |
| Manufacturing process technology | 5 nm vs 8 nm |
| Thermal Design Power (TDP) | 120 Watt vs 130 Watt |
| Benchmarks | |
| Geekbench - OpenCL | 95143 vs 78981 |
Reasons to consider the NVIDIA RTX A3000 Mobile
- 85.3x more pipelines: 4096 vs 48
| Pipelines | 4096 vs 48 |
Compare benchmarks
GPU 1: Apple M1 Ultra 48-core
GPU 2: NVIDIA RTX A3000 Mobile
| Geekbench - OpenCL |
|
|
| Name | Apple M1 Ultra 48-core | NVIDIA RTX A3000 Mobile |
|---|---|---|
| Geekbench - OpenCL | 95143 | 78981 |
| PassMark - G2D Mark | 526 | |
| PassMark - G3D Mark | 12647 | |
| GFXBench 4.0 - Car Chase Offscreen (Frames) | 20429 | |
| GFXBench 4.0 - Car Chase Offscreen (Fps) | 20429 | |
| GFXBench 4.0 - Manhattan (Frames) | 3710 | |
| GFXBench 4.0 - Manhattan (Fps) | 3710 | |
| GFXBench 4.0 - T-Rex (Frames) | 3356 | |
| GFXBench 4.0 - T-Rex (Fps) | 3356 |
Compare specifications (specs)
| Apple M1 Ultra 48-core | NVIDIA RTX A3000 Mobile | |
|---|---|---|
Essentials |
||
| Launch date | 18 Mar 2022 | |
| Place in performance rating | 177 | 174 |
| Architecture | Ampere | |
| Code name | GA104 | |
Technical info |
||
| Core clock speed | 1296 MHz | 1080 MHz |
| Manufacturing process technology | 5 nm | 8 nm |
| Peak Single Precision (FP32) Performance | 15.925 TFLOPS | 12.78 TFLOPS |
| Pipelines | 48 | 4096 |
| Render output units | 192 | |
| Thermal Design Power (TDP) | 120 Watt | 130 Watt |
| Boost clock speed | 1560 MHz | |
| Peak Double Precision (FP64) Performance | 199.7 GFLOPS (1:64) | |
| Peak Half Precision (FP16) Performance | 12.78 TFLOPS (1:1) | |
| Pixel fill rate | 99.84 GPixel/s | |
| Texture fill rate | 199.7 GTexel/s | |
| Transistor count | 17400 million | |
Memory |
||
| Memory bandwidth | 819.2 GB/s | 288 GB/s |
| Memory bus width | 1024 bit | 192 bit |
| Memory type | LPDDR5-6400 | GDDR6 |
| Maximum RAM amount | 6 GB | |
| Memory clock speed | 1500 MHz (12 Gbps effective) | |
Video outputs and ports |
||
| Display Connectors | No outputs | |
Compatibility, dimensions and requirements |
||
| Interface | PCIe 4.0 x16 | |
| Supplementary power connectors | None | |
API support |
||
| DirectX | 12.2 | |
| OpenCL | 3.0 | |
| OpenGL | 4.6 | |
| Shader Model | 6.6 | |
| Vulkan | ||
