AMD Instinct MI325X vs NVIDIA L40S
How the AMD Instinct MI325X and NVIDIA L40S 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 → | ADA LOVELACE NVIDIA L40S View Product → |
|---|---|---|
| Pricing | ||
| Price | Not sold by NVNexus | $11,160.00 |
| Overview | ||
| Architecture | AMD CDNA 3 | Ada Lovelace |
| Memory | ||
| Memory | 256 GB HBM3E | 48 GB GDDR6 with ECC |
| 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) | 91.6 TFLOPS |
| FP64 Tensor | 163.4 TFLOPS (matrix) | – |
| TF32 Tensor | 653.7 TFLOPS / 1,307 (sparse) | 366 TFLOPS (Sparse) |
| FP16/BF16 Tensor | 1,307 TFLOPS / 2,615 (sparse) | 733 TFLOPS (Sparse) |
| FP8 Tensor | 2,615 TFLOPS / 5,230 (sparse) | 1,466 TFLOPS (Sparse) |
| INT8 Tensor | 2,615 TOPS / 5,230 (sparse) | – |
| RT Performance | – | 212 TFLOPS |
| Platform | ||
| Interface | PCIe Gen5 x16 | PCIe Gen4 |
| NVLink / Infinity Fabric | Infinity Fabric, 896 GB/s aggregate | – |
| TDP | 1000W | 350W |
| Form Factor | OAM module (8-GPU platform) | PCIe dual-slot |
| 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 L40S vs NVIDIA L4 →
- NVIDIA L40S vs NVIDIA L40 →
- NVIDIA L40S vs NVIDIA RTX 2000 Ada Generation →
- NVIDIA L40S vs NVIDIA RTX 4000 Ada Generation →