Data Center GPU Max Subsystem: specs and benchmarks
Summary
Intel started Data Center GPU Max Subsystem sales 10 January 2023. This is a Generation 12.5 architecture desktop card based on 10 nm manufacturing process and primarily aimed at designers. 128 GB of HBM2e memory clocked at 1.57 GHz are supplied, and together with 8192 Bit memory interface this creates a bandwidth of 3,205 GB/s.
Compatibility-wise, this is a dual-slot graphics card attached via PCIe 5.0 x16 interface. Its manufacturer default version has a length of 267 mm. 1x 16-pin power connector is required, and power consumption is at 2400 Watt.
Primary details
Some basic facts about Data Center GPU Max Subsystem: architecture, market segment, release date etc.
| Place in the ranking | not rated | |
| Place by popularity | not in top-100 | |
| Architecture | Generation 12.5 (2021−2023) | |
| GPU code name | Ponte Vecchio | |
| Market segment | Workstation | |
| Release date | 10 January 2023 (1 year ago) |
Detailed specifications
Data Center GPU Max Subsystem's specs such as number of shaders, GPU base clock, manufacturing process, texturing and calculation speed. These parameters indirectly speak of Data Center GPU Max Subsystem's performance, but for precise assessment you have to consider its benchmark and gaming test results.
| Pipelines / CUDA cores | 16384 | of 21760 (GeForce RTX 5090) |
| Core clock speed | 900 MHz | of 2670 MHz (Arc B580) |
| Boost clock speed | 1600 MHz | of 3599 MHz (Radeon RX 7990 XTX) |
| Number of transistors | 100,000 million | of 208,000 million (B200 SXM 192 GB) |
| Manufacturing process technology | 10 nm | of 3 nm (Arc Graphics 140V) |
| Power consumption (TDP) | 2400 Watt | |
| Texture fill rate | 1,638 | of 2,554 (Radeon Instinct MI300X) |
| Floating-point processing power | 52.43 TFLOPS | of 109.7 (GeForce RTX 5090) |
| TMUs | 1024 | of 1280 (Data Center GPU Max NEXT) |
| Tensor Cores | 1024 | of 1216 (Radeon Instinct MI300X) |
| Ray Tracing Cores | 128 | of 170 (GeForce RTX 5090) |
Form factor & compatibility
This section provides details about the physical dimensions of Data Center GPU Max Subsystem and its compatibility with other computer components. This information is useful when selecting a computer configuration or upgrading an existing one. For desktop graphics cards, it includes details about the interface and bus (for motherboard compatibility) and additional power connectors (for power supply compatibility).
| Interface | PCIe 5.0 x16 | |
| Length | 267 mm | |
| Width | 2-slot | |
| Supplementary power connectors | 1x 16-pin |
VRAM capacity and type
Parameters of memory installed on Data Center GPU Max Subsystem: its type, size, bus, clock and resulting bandwidth. Note that GPUs integrated into processors have no dedicated memory and use a shared part of system RAM instead.
| Memory type | HBM2e | |
| Maximum RAM amount | 128 GB | of 294912 (Radeon Instinct MI325X) |
| Memory bus width | 8192 Bit | |
| Memory clock speed | 1565 MHz | of 20000 (RTX 5000 Ada Generation Mobile) |
| Memory bandwidth | 3,205 GB/s | of 5,171 GB/s (Radeon Instinct MI300X) |
Connectivity and outputs
Types and number of video connectors present on Data Center GPU Max Subsystem. As a rule, this section is relevant only for desktop reference graphics cards, since for notebook ones the availability of certain video outputs depends on the laptop model, while non-reference desktop models can (though not necessarily will) bear a different set of video ports.
| Display Connectors | No outputs |
API compatibility
APIs supported by Data Center GPU Max Subsystem, sometimes including their particular versions.
| DirectX | 12 (12_1) | |
| Shader Model | 6.6 | |
| OpenGL | 4.6 | |
| OpenCL | 3.0 | |
| Vulkan | N/A |
Similar GPUs
Here is our recommendation of several graphics cards that are more or less close in performance to the one reviewed.
Recommended processors
These processors are most commonly used with Data Center GPU Max Subsystem according to our statistics.
