Apple M2 Ultra 60-Core GPU
vs
NVIDIA RTX A6000
GPU comparison with benchmarksThe Apple M2 Ultra 60-Core GPU is based on the Apple M2 Ultra (60-GPU) (M2) and has 64 GB LPDDR5 graphics memory with a bandwidth of 819 GB/s.
The NVIDIA RTX A6000 is based on the NVIDIA RTX A6000 (Ampere) and has 48 GB GDDR6 graphics memory with a bandwidth of 768 GB/s. |
||
GPUThe Apple M2 Ultra 60-Core GPU has the M2 Ultra graphics chip installed, which is based on the M2 architecture. The NVIDIA RTX A6000 is based on the graphics chip GA102, which comes from the Ampere architecture. |
||
| Apple M2 Ultra 60-Core GPU | GPU | NVIDIA RTX A6000 |
| Apple M2 Ultra (60-GPU) | Based on | NVIDIA RTX A6000 |
| M2 Ultra | GPU Chip | GA102 |
| M2 | Architecture | Ampere |
| 960 | Streaming Multiprocessors | 84 |
| 7680 | Shader | 10752 |
| 0 | Render Output Units | 112 |
| 0 | Texture Units | 336 |
| 0 | Raytracing Cores | 84 |
MemoryThe graphics memory of the Apple M2 Ultra 60-Core GPU clocks at 3.200 GHz, which corresponds to a speed of 0.0 Gbps. The graphics memory speed of the NVIDIA RTX A6000 is 16.0 Gbps and the clock speed is 2.000 GHz. |
||
| 64 GB | Memory Size | 48 GB |
| LPDDR5 | Memory Type | GDDR6 |
| 3.200 GHz | Memory Clock | 2.000 GHz |
| 0.0 Gbps | Memory Speed | 16.0 Gbps |
| 819 GB/s | Memory bandwidth | 768 GB/s |
| 1024 bit | Memory Interface | 384 bit |
Clock SpeedsThe clock frequency of a graphics card determines the speed in connection with the graphics architecture. |
||
| 1.400 GHz | Base Clock | 1.410 GHz |
| Boost Clock | 1.800 GHz | |
| Avg (Game) Clock | ||
| No | Overclocking | Yes |
Thermal DesignThe Apple M2 Ultra 60-Core GPU is powered by connectors. The TDP (Thermal Design Power) of the graphics card is --. The NVIDIA RTX A6000 has 1 x 8-Pin PCIe power connectors that supply it with energy. The manufacturer specifies the TDP of the card as 300 W. |
||
| -- | TDP | 300 W |
| -- | TDP (up) | -- |
| Unknown | Tjunction max | 93 °C |
| PCIe-Power | 1 x 8-Pin | |
Cooler & FansThe Apple M2 Ultra 60-Core GPU is equipped with a total of 0 -- main fans. The NVIDIA RTX A6000 has 1 Radial main fans that cool the GPU and memory. |
||
| -- | Fan-Type | Radial |
| -- | Fan 1 | 1 x 65 mm |
| -- | Fan 2 | -- |
| Air cooling | Cooler-Type | Air cooling |
| -- | Noise (Idle) | dB |
| -- | Noise (Load) | -- |
ConnectivityUp to 8 screens can be operated with the Apple M2 Ultra 60-Core GPU. The NVIDIA RTX A6000 supports the operation of a maximum of 4 monitors. |
||
| 8 | Max. Displays | 4 |
| -- | HDCP-Version | 2.3 |
| -- | HDMI Ports | -- |
| -- | DP Ports | 4x DP v1.4 |
| -- | DVI Ports | -- |
| -- | VGA Ports | -- |
| -- | USB-C Ports | -- |
FeaturesetWith the Apple M2 Ultra 60-Core GPU it is possible to operate a screen with a maximum resolution of up to 7680x4320 pixels. The maximum supported resolution of the NVIDIA RTX A6000 is 7680x4320 pixels. |
||
| 7680x4320 | Max. resolution | 7680x4320 |
| 0 | DirectX | 12_2 (Ultimate) |
| No | Raytracing | Yes |
| Yes | DLSS / FSR | Yes |
| No LED lighting | LED | No LED lighting |
Supported Video CodecsThe support and acceleration of certain video codecs can have a positive impact on the lower energy consumption and less waste heat from the graphics card. |
||
| Decode / Encode | h264 | Decode / Encode |
| Decode / Encode | h265 / HEVC | Decode / Encode |
| No | AV1 | Decode |
| Decode | VP8 | Decode |
| Decode / Encode | VP9 | Decode |
DimensionsThe Apple M2 Ultra 60-Core GPU is connected to the system via Integrated graphics lanes and requires -- space in the housing. The NVIDIA RTX A6000 needs the space of 2 PCIe-Slots in the case and has a PCIe 4.0 x 16 Lanes interface. |
||
| -- | Length | 267 mm |
| -- | Height | 112 mm |
| -- | Width | -- |
| -- | Width (Slots) | 2 PCIe-Slots |
| -- | Weight | -- |
| Integrated graphics | GPU Interface | PCIe 4.0 x 16 |
| No | SFF-Ready | No |
Additional dataThe Apple M2 Ultra 60-Core GPU has been manufactured with a structure width of 5 nanometers since Q2/2023. The NVIDIA RTX A6000 came on the market in Q4/2020 and will have a structure width of 8 nanometers manufactured. |
||
| -- | Part-no | -- |
| Q2/2023 | Release date | Q4/2020 |
| -- | Launch Price | 4,649 $ |
| 5 nm | Structure size | 8 nm |
| -- | Documents | data sheet |
1.400 GHz, 64 GB (-- TDP)
Buy this graphic card at amazon!
1.410 GHz, 48 GB (300 W TDP)
Buy this graphic card at amazon!
Rate these graphics cards now
Benchmark results
3DMark Benchmark (DirectX, Raytracing)
3DMark is a benchmark program that determines the performance of certain components of a computer and then reports the performance as a numerical value.
Time Spy Extreme Graphics score
|
NVIDIA RTX A6000
48 GB GDDR6 |
||
Port Royal (Raytracing)
|
|
NVIDIA RTX A6000
48 GB GDDR6 |
||
Speed Way Graphics Score (Raytracing)
|
|
NVIDIA RTX A6000
48 GB GDDR6 |
||
Battlefield 5
Battlefield 5 is a visually stunning game that is ideal as a graphics card benchmark. We test the game with maximum details on Windows 10.
1920x1080 (1080p)
|
|
NVIDIA RTX A6000
48 GB GDDR6 |
||
Geekbench 6 (OpenCL, Vulkan, Metal)
Geekbench 6 is a cross-platform benchmark for main processors, which also carries out 3 different graphics benchmarks and outputs them in the form of a numerical value.
Geekbench 6 - OpenCL
|
Apple M2 Ultra 60-Core GPU
64 GB LPDDR5 |
||
|
|
NVIDIA RTX A6000
48 GB GDDR6 |
||
Geekbench 6 - Vulkan
|
|
NVIDIA RTX A6000
48 GB GDDR6 |
||
Geekbench 6 - Metal
|
|
Apple M2 Ultra 60-Core GPU
64 GB LPDDR5 |
||
FP32 Performance (Single-precision TFLOPS)
The theoretical computing power of the graphics card with single precision (32 bit) in TFLOPS indicates how many trillion FP32 floating point operations the graphics card (GPU) can perform per second.
FP32 (TFLOPS)
|
|
Apple M2 Ultra 60-Core GPU
64 GB LPDDR5 |
||
|
|
NVIDIA RTX A6000
48 GB GDDR6 |
||
Popular comparisons
