GeForce RTX 5080 SUPER vs Radeon Instinct MI25
Contents
Primary details
GPU architecture, market segment, value for money and other general parameters compared.
| Place in the ranking | 472 | not rated |
| Place by popularity | not in top-100 | not in top-100 |
| Power efficiency | 2.68 | no data |
| Architecture | GCN 5.0 (2017−2020) | Blackwell 2.0 (2025−2026) |
| GPU code name | Vega 10 | GB203 |
| Market segment | Workstation | Desktop |
| Release date | 27 June 2017 (8 years ago) | 2026 |
| Launch price (MSRP) | no data | $999 |
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 | 4096 ×2 | 10752 |
| Core clock speed | 1400 MHz | 2295 MHz |
| Boost clock speed | 1500 MHz | 2617 MHz |
| Number of transistors | 12,500 million | 45,600 million |
| Manufacturing process technology | 14 nm | 5 nm |
| Power consumption (TDP) | 300 Watt | 415 Watt |
| Texture fill rate | 384.0 ×2 | 879.3 |
| Floating-point processing power | 12.29 TFLOPS ×2 | 56.28 TFLOPS |
| ROPs | 64 ×2 | 112 |
| TMUs | 256 ×2 | 336 |
| Tensor Cores | no data | 336 |
| Ray Tracing Cores | no data | 84 |
| L1 Cache | 1 MB | 10.5 MB |
| L2 Cache | 4 MB | 64 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 | 267 mm | 304 mm |
| Width | 2-slot | 2-slot |
| Supplementary power connectors | 2x 8-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 | HBM2 | GDDR7 |
| Maximum RAM amount | 16 GB ×2 | 24 GB |
| Memory bus width | 2048 Bit ×2 | 256 Bit |
| Memory clock speed | 852 MHz | 2000 MHz |
| Memory bandwidth | 436.2 GB/s ×2 | 1.02 TB/s |
| Resizable BAR | - | + |
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 | 1x HDMI 2.1b, 3x DisplayPort 2.1b |
| HDMI | - | + |
API and SDK support
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | 12 (12_1) | 12 Ultimate (12_2) |
| Shader Model | 6.4 | 6.8 |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.0 | 3.0 |
| Vulkan | 1.1.125 | 1.4 |
| CUDA | - | 12.0 |
| DLSS | - | + |
Pros & cons summary
| Maximum RAM amount | 16 GB | 24 GB |
| Chip lithography | 14 nm | 5 nm |
| Power consumption (TDP) | 300 Watt | 415 Watt |
Instinct MI25 has 38.3% lower power consumption.
RTX 5080 SUPER, on the other hand, has a 50% higher maximum VRAM amount, and a 180% more advanced lithography process.
We couldn't decide between Radeon Instinct MI25 and GeForce RTX 5080 SUPER. We've got no test results to judge.
Be aware that Radeon Instinct MI25 is a workstation graphics card while GeForce RTX 5080 SUPER is a desktop one.
Other comparisons
We selected several comparisons of graphics cards with performance close to those reviewed, providing you with more options to consider.
