Brand: AMD | Category: GPUs
SKU: AMD-100300000128 | Part #: 100-300000128 | MPN: 100-300000128
Contact for Pricing — Request a Quote
The AMD Instinct MI325X 256GB OAM Accelerator from AMD is enterprise-grade GPUs hardware built for data centers. The AMD Instinct MI325X is a high-memory AI accelerator built on AMD's CDNA3 compute architecture, delivering a substantial leap in memory capacity for large-scale AI and HPC workloads. At its core, the MI325X features 256GB of HBM3e memory — double the capacity of the MI300X — providing an expansive on-device memory pool that enables larger AI models, bigger batch sizes, and reduced reliance on multi-node memory offloading. The accelerator is packaged in the Open Accelerator Available in brand new condition. AMD gpus products are trusted by enterprises and data centers worldwide. Available from Omnixon Global. Contact our sales team to request a quote.
| Brand | AMD |
| Category | GPUs |
| SKU | AMD-100300000128 |
| Part Number | 100-300000128 |
| Condition | New |
| Manufacturer Part Number | 100-300000128 |
| Product Name | AMD Instinct MI325X |
| Architecture | CDNA3 |
| Form Factor | OAM (Open Accelerator Module) |
| Memory Capacity | 256 GB |
| Memory Type | HBM3e |
| Memory Bandwidth | 6.0 TB/s |
| Compute Units | 304 |
| Peak FP64 Throughput | 163.4 TFLOPS |
| Peak FP32 Throughput | 163.4 TFLOPS |
| Peak FP16 Throughput | 1.3 PFLOPS |
| Peak BF16 Throughput | 1.3 PFLOPS |
| Peak FP8 Throughput | 2.6 PFLOPS |
| Interconnect | AMD Infinity Fabric |
| TDP | 750 W |
| Supported Precisions | FP64, FP32, FP16, BF16, FP8, INT8 |
| Software Platform | AMD ROCm (open-source) |
| Supported Frameworks | PyTorch, TensorFlow, JAX (via ROCm) |