Data Center GPU Max Subsystem vs Radeon Instinct MI6
Contents
Primary details
GPU architecture, market segment, value for money and other general parameters compared.
| Place in the ranking | not rated | not rated |
| Place by popularity | not in top-100 | not in top-100 |
| Architecture | GCN 4.0 (2016−2020) | Generation 12.5 (2021−2023) |
| GPU code name | Ellesmere | Ponte Vecchio |
| Market segment | Workstation | Workstation |
| Release date | 12 December 2016 (9 years ago) | 10 January 2023 (3 years ago) |
Detailed specifications
General parameters such as number of shaders, GPU core base clock and boost clock speeds, manufacturing process, texturing and calculation speed. Note that power consumption of some graphics cards can well exceed their nominal TDP, especially when overclocked.
| Pipelines / CUDA cores | 2304 | 16384 ×4 |
| Core clock speed | 1120 MHz | 900 MHz |
| Boost clock speed | 1233 MHz | 1600 MHz |
| Number of transistors | 5,700 million | 100,000 million |
| Manufacturing process technology | 14 nm | 10 nm |
| Power consumption (TDP) | 150 Watt | 2400 Watt |
| Texture fill rate | 177.6 | 1,638 ×4 |
| Floating-point processing power | 5.682 TFLOPS | 52.43 TFLOPS ×4 |
| ROPs | 32 | no data |
| TMUs | 144 | 1024 ×4 |
| Tensor Cores | no data | 1024 ×4 |
| Ray Tracing Cores | no data | 128 ×4 |
| L1 Cache | 576 KB | 64 MB |
| L2 Cache | 2 MB | 408 MB |
Form factor & compatibility
Information on compatibility with other computer components. Useful when choosing a future computer configuration or upgrading an existing one. For desktop graphics cards it's interface and bus (motherboard compatibility), additional power connectors (power supply compatibility).
| Interface | PCIe 3.0 x16 | PCIe 5.0 x16 |
| Length | 241 mm | 267 mm |
| Width | 1-slot | 2-slot |
| Supplementary power connectors | 1x 6-pin | 1x 16-pin |
VRAM capacity and type
Parameters of VRAM installed: its type, size, bus, clock and resulting bandwidth. Integrated GPUs have no dedicated video RAM and use a shared part of system RAM.
| Memory type | GDDR5 | HBM2e |
| Maximum RAM amount | 8 GB | 128 GB ×4 |
| Memory bus width | 256 Bit | 8192 Bit ×4 |
| Memory clock speed | 1750 MHz | 1565 MHz |
| Memory bandwidth | 224.0 GB/s | 3,205 GB/s ×4 |
Connectivity and outputs
This section shows the types and number of video connectors on each GPU. The data applies specifically to desktop reference models (for example, NVIDIA’s Founders Edition). OEM partners often modify both the number and types of ports. On notebook GPUs, video‐output options are determined by the laptop’s design rather than the graphics chip itself.
| Display Connectors | No outputs | No outputs |
API and SDK support
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | 12 (12_0) | 12 (12_1) |
| Shader Model | 6.4 | 6.6 |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.0 | 3.0 |
| Vulkan | 1.2.131 | N/A |
| DLSS | - | + |
Pros & cons summary
| Recency | 12 December 2016 | 10 January 2023 |
| Maximum RAM amount | 8 GB | 128 GB |
| Chip lithography | 14 nm | 10 nm |
| Power consumption (TDP) | 150 Watt | 2400 Watt |
Instinct MI6 has 1500% lower power consumption.
Data Center GPU Max Subsystem, on the other hand, has an age advantage of 6 years, a 1500% higher maximum VRAM amount, and a 40% more advanced lithography process.
We couldn't decide between Radeon Instinct MI6 and Data Center GPU Max Subsystem. We've got no test results to judge.
Other comparisons
We selected several comparisons of graphics cards with performance close to those reviewed, providing you with more options to consider.
