Radeon Instinct MI300A vs Pro Vega II Duo
Contents
Primary details
GPU architecture, market segment, value for money and other general parameters compared.
| Place in the ranking | 178 | not rated |
| Place by popularity | not in top-100 | not in top-100 |
| Cost-effectiveness evaluation | 2.40 | no data |
| Power efficiency | 5.31 | no data |
| Architecture | GCN 5.1 (2018−2022) | CDNA 3.0 (2023−2024) |
| GPU code name | Vega 20 | Aqua Vanjaram |
| Market segment | Workstation | Workstation |
| Release date | 3 June 2019 (6 years ago) | 6 December 2023 (2 years ago) |
| Launch price (MSRP) | $4,399 | no data |
Cost-effectiveness evaluation
The higher the ratio, the better. We use the manufacturer's recommended prices.
Performance to price scatter graph
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 | 19456 |
| Core clock speed | 1400 MHz | 1000 MHz |
| Boost clock speed | 1720 MHz | 2100 MHz |
| Number of transistors | 13,230 million | 153,000 million |
| Manufacturing process technology | 7 nm | 5 nm |
| Power consumption (TDP) | 475 Watt | 750 Watt |
| Texture fill rate | 440.3 ×2 | 2,554 |
| Floating-point processing power | 14.09 TFLOPS ×2 | 81.72 TFLOPS |
| ROPs | 64 ×2 | no data |
| TMUs | 256 ×2 | 1216 |
| Tensor Cores | no data | 1216 |
| L1 Cache | 1 MB | 4.8 MB |
| L2 Cache | 4 MB | 16 MB |
| L3 Cache | no data | 256 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 | Apple MPX | PCIe 5.0 x16 |
| Width | Quad-slot | OAM Module |
| Supplementary power connectors | None | 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 | HBM2 | HBM3 |
| Maximum RAM amount | 32 GB ×2 | 192 GB |
| Memory bus width | 4096 Bit ×2 | 8192 Bit |
| Memory clock speed | 1000 MHz | 2525 MHz |
| Memory bandwidth | 1.02 TB/s ×2 | 10.3 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 | 1x HDMI 2.0b, 4x Thunderbolt | No outputs |
| HDMI | + | - |
API and SDK support
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | 12 (12_1) | N/A |
| Shader Model | 6.7 | N/A |
| OpenGL | 4.6 | N/A |
| OpenCL | 2.1 | 3.0 |
| Vulkan | 1.3 | N/A |
| DLSS | - | + |
Pros & cons summary
| Recency | 3 June 2019 | 6 December 2023 |
| Maximum RAM amount | 32 GB | 192 GB |
| Chip lithography | 7 nm | 5 nm |
| Power consumption (TDP) | 475 Watt | 750 Watt |
Pro Vega II Duo has 58% lower power consumption.
Instinct MI300A, on the other hand, has an age advantage of 4 years, a 500% higher maximum VRAM amount, and a 40% more advanced lithography process.
We couldn't decide between Radeon Pro Vega II Duo and Radeon Instinct MI300A. 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.
