AMD Instinct MI325X vs NVIDIA Rubin CPX
How the AMD Instinct MI325X and NVIDIA Rubin CPX compare across memory, compute, power and form factor, with the stronger figure highlighted on each row. Vendor-specific figures (CUDA vs stream processors, Tensor vs matrix cores) are listed on their own rows.
| Specification | CDNA 3 AMD Instinct MI325X NVIDIA alternative: NVIDIA H200 SXM → |  RUBIN NVIDIA Rubin CPX View Product → |
|---|---|---|
| Pricing | ||
| Price | Not sold by NVNexus | – |
| Overview | ||
| Architecture | AMD CDNA 3 | Rubin (CPX variant) |
| Memory | ||
| Memory | 256 GB HBM3E | HBM4 (capacity per partner configuration) |
| Memory Bandwidth | 6 TB/s | – |
| Memory Interface | 8192-bit | – |
| Compute | ||
| Stream Processors (AMD) | 19,456 (304 CUs) | – |
| Matrix Cores / AI Accelerators (AMD) | 1,216 | – |
| FP32 | 163.4 TFLOPS (matrix) | – |
| FP64 Tensor | 163.4 TFLOPS (matrix) | – |
| TF32 Tensor | 653.7 TFLOPS / 1,307 (sparse) | – |
| FP16/BF16 Tensor | 1,307 TFLOPS / 2,615 (sparse) | – |
| FP8 Tensor | 2,615 TFLOPS / 5,230 (sparse) | – |
| INT8 Tensor | 2,615 TOPS / 5,230 (sparse) | – |
| Platform | ||
| Interface | PCIe Gen5 x16 | – |
| NVLink / Infinity Fabric | Infinity Fabric, 896 GB/s aggregate | NVLink 6, PCIe Gen 6 |
| TDP | 1000W | – |
| Form Factor | OAM module (8-GPU platform) | SXM / rack-integrated |
| Cooling | Passive (chassis airflow) | – |
| Transistors | 153 billion | – |
Not sure which fits?
Talk to an Expert → Talk it through with a specialist
Tell us your workload and we will recommend the right GPU, configuration, and sourcing options.
More Comparisons
- AMD Instinct MI325X vs AMD Instinct MI300X →
- AMD Instinct MI325X vs AMD Instinct MI210 →
- AMD Instinct MI325X vs AMD Instinct MI350X →
- AMD Instinct MI325X vs AMD Instinct MI355X →
- AMD Instinct MI325X vs NVIDIA H200 SXM →
- AMD Instinct MI325X vs NVIDIA A10 →
- NVIDIA Rubin CPX vs NVIDIA A10 →
- NVIDIA Rubin CPX vs NVIDIA A100 80GB →
- NVIDIA Rubin CPX vs NVIDIA A16 →
- NVIDIA Rubin CPX vs NVIDIA A2 →