AMD Radeon Instinct MI300A: specs and benchmarks
Contents
Summary
AMD started Radeon Instinct MI300A sales 6 December 2023. This is a CDNA 3.0 architecture desktop card based on 5 nm manufacturing process and primarily aimed at designers. 192 GB of HBM3 memory clocked at 2.53 GHz are supplied, and together with 8192 Bit memory interface this creates a bandwidth of 10.3 TB/s.
Compatibility-wise, this is a oam module graphics card attached via PCIe 5.0 x16 interface. No additional power connector is required, and power consumption is at 750 Watt.
Primary details
Some basic facts about Radeon Instinct MI300A: architecture, market segment, release date etc.
| Place in the ranking | not rated | |
| Place by popularity | not in top-100 | |
| Architecture | CDNA 3.0 (2023−2024) | |
| GPU code name | Aqua Vanjaram | |
| Market segment | Workstation | |
| Release date | 6 December 2023 (1 year ago) |
Detailed specifications
Radeon Instinct MI300A's specs such as number of shaders, GPU base clock, manufacturing process, texturing and calculation speed. These parameters indirectly speak of Radeon Instinct MI300A's performance, but for precise assessment you have to consider its benchmark and gaming test results.
| Pipelines / CUDA cores | 19456 | of 960 (GeForce GTX 660) |
| Core clock speed | 1000 MHz | of 980 (GeForce GT 755M SLI) |
| Boost clock speed | 2100 MHz | of 1000 (HD Graphics (Haswell)) |
| Number of transistors | 153,000 million | of 100,000 million (Data Center GPU Max 1100) |
| Manufacturing process technology | 5 nm | of 0.003 MB (Arc Graphics 140V) |
| Power consumption (TDP) | 750 Watt | of 235 (FirePro S9150) |
| Texture fill rate | 2,554 | of 1,968.0 (RTX PRO 6000 Blackwell Server) |
| Floating-point processing power | 81.72 TFLOPS | of 126 (RTX PRO 6000 Blackwell Server) |
| TMUs | 1216 | of 896 (Data Center GPU Max 1350) |
| Tensor Cores | 1216 | of 896 (Data Center GPU Max 1350) |
| L1 Cache | 4.8 MB | of 64 MB (Data Center GPU Max 1550) |
| L2 Cache | 16 MB | of 408 MB (Data Center GPU Max 1350) |
| L3 Cache | 256 MB | of 256 MB (Radeon Instinct MI300X) |
Form factor & compatibility
This section provides details about the physical dimensions of Radeon Instinct MI300A 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 | |
| Width | OAM Module | |
| Supplementary power connectors | None |
VRAM capacity and type
Parameters of memory installed on Radeon Instinct MI300A: 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 | HBM3 | |
| Maximum RAM amount | 192 GB | of 288 GB (Radeon Instinct MI325X) |
| Memory bus width | 8192 Bit | of 384 (GeForce GTX 980 Ti) |
| Memory clock speed | 2525 MHz | of 16384000 MB (GeForce RTX 4050 Mobile) |
| Memory bandwidth | 10.3 TB/s | of 983040 MB (GeForce RTX 5080) |
| Resizable BAR | + |
Connectivity and outputs
Types and number of video connectors present on Radeon Instinct MI300A. 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 and SDK support
APIs supported by Radeon Instinct MI300A, sometimes including their particular versions.
| DirectX | N/A | |
| Shader Model | N/A | |
| OpenGL | N/A | of 4.6 (RTX PRO 5000 Blackwell) |
| OpenCL | 3.0 | |
| Vulkan | N/A | |
| DLSS | + |
NVIDIA equivalent
According to our data, the closest NVIDIA alternative to Radeon Instinct MI300A is RTX PRO 5000 Blackwell.
Similar GPUs
Here is our recommendation of several graphics cards that are more or less close in performance to the one reviewed.
