Radeon Instinct MI308X vs GeForce RTX 5090 Mobile
Contents
Primary details
GPU architecture, market segment, value for money and other general parameters compared.
| Place in the ranking | 13 | not rated |
| Place by popularity | not in top-100 | not in top-100 |
| Power efficiency | 58.41 | no data |
| Architecture | Blackwell 2.0 (2025) | CDNA 3.0 (2023−2024) |
| GPU code name | GB203 | Aqua Vanjaram |
| Market segment | Laptop | Workstation |
| Release date | 27 March 2025 (less than a year ago) | 6 December 2023 (1 year 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 | 10496 | 19456 |
| Core clock speed | 990 MHz | 1000 MHz |
| Boost clock speed | 1515 MHz | 2100 MHz |
| Number of transistors | 45,600 million | 153,000 million |
| Manufacturing process technology | 5 nm | 5 nm |
| Power consumption (TDP) | 95 Watt | 750 Watt |
| Texture fill rate | 496.9 | 2,554 |
| Floating-point processing power | 31.8 TFLOPS | 81.72 TFLOPS |
| ROPs | 112 | no data |
| TMUs | 328 | 1216 |
| Tensor Cores | 328 | 1216 |
| Ray Tracing Cores | 82 | no data |
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 5.0 x16 | PCIe 5.0 x16 |
| Width | no data | OAM Module |
| Supplementary power connectors | no data | None |
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 | GDDR7 | HBM3 |
| Maximum RAM amount | 24 GB | 192 GB |
| Memory bus width | 256 Bit | 8192 Bit |
| Memory clock speed | 1750 MHz | 2525 MHz |
| Memory bandwidth | 896.0 GB/s | 10.3 TB/s |
| Resizable BAR | + | + |
Connectivity and outputs
Types and number of video connectors present on the reviewed GPUs. As a rule, data in this section is precise only for desktop reference ones (so-called Founders Edition for NVIDIA chips). OEM manufacturers may change the number and type of output ports, while for notebook cards availability of certain video outputs ports depends on the laptop model rather than on the card itself.
| Display Connectors | Portable Device Dependent | No outputs |
API and SDK compatibility
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | 12 Ultimate (12_2) | N/A |
| Shader Model | 6.8 | N/A |
| OpenGL | 4.6 | N/A |
| OpenCL | 3.0 | 3.0 |
| Vulkan | 1.4 | N/A |
| CUDA | 12.0 | - |
| DLSS | + | + |
Pros & cons summary
| Recency | 27 March 2025 | 6 December 2023 |
| Maximum RAM amount | 24 GB | 192 GB |
| Power consumption (TDP) | 95 Watt | 750 Watt |
RTX 5090 Mobile has an age advantage of 1 year, and 689.5% lower power consumption.
Instinct MI308X, on the other hand, has a 700% higher maximum VRAM amount.
We couldn't decide between GeForce RTX 5090 Mobile and Radeon Instinct MI308X. We've got no test results to judge.
Be aware that GeForce RTX 5090 Mobile is a notebook card while Radeon Instinct MI308X is a workstation one.
Other comparisons
We selected several comparisons of graphics cards with performance close to those reviewed, providing you with more options to consider.
