AMD Instinct MI355X vs NVIDIA L40
How the AMD Instinct MI355X and NVIDIA L40 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 4 AMD Instinct MI355X NVIDIA alternative: NVIDIA B200 → | ADA LOVELACE NVIDIA L40 View Product → |
|---|---|---|
| Pricing | ||
| Price | Not sold by NVNexus | $10,800.00 |
| Overview | ||
| Architecture | AMD CDNA 4 | Ada Lovelace (4nm) |
| Memory | ||
| Memory | 288 GB HBM3E | 48 GB GDDR6 with ECC |
| Memory Bandwidth | 8 TB/s | 864 GB/s |
| Memory Interface | 8192-bit | 384-bit |
| Compute | ||
| CUDA Cores | – | 18,176 |
| Stream Processors (AMD) | 16,384 (256 CUs) | – |
| Tensor Cores | – | 568 |
| Matrix Cores / AI Accelerators (AMD) | 1,024 | – |
| RT Cores / Ray Accelerators | – | 142 |
| FP32 | 157.3 TFLOPS | – |
| FP64 Tensor | 78.6 TFLOPS | – |
| FP16/BF16 Tensor | 2.5 PFLOPS / 5 (sparse) TFLOPS | – |
| FP8 Tensor | 5 PFLOPS / 10.1 (sparse) TFLOPS | – |
| FP4 Tensor | 10.1 PFLOPS TFLOPS | – |
| Platform | ||
| Interface | PCIe Gen5 x16 | PCIe Gen4 x16 |
| NVLink / Infinity Fabric | Infinity Fabric, 1,075 GB/s aggregate | – |
| TDP | 1400W | 300W |
| Form Factor | OAM module (8-GPU platform) | 4.4" H × 10.5" L, dual slot, passive |
| Display Outputs | – | 4× DisplayPort 1.4a |
| Cooling | Liquid cooled | – |
| Transistors | 185 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 MI355X vs AMD Instinct MI350X →
- AMD Instinct MI355X vs AMD Instinct MI210 →
- AMD Instinct MI355X vs AMD Instinct MI300X →
- AMD Instinct MI355X vs AMD Instinct MI325X →
- AMD Instinct MI355X vs NVIDIA B200 →
- AMD Instinct MI355X vs NVIDIA A10 →
- NVIDIA L40 vs NVIDIA L4 →
- NVIDIA L40 vs NVIDIA L40S →
- NVIDIA L40 vs NVIDIA RTX 2000 Ada Generation →
- NVIDIA L40 vs NVIDIA RTX 4000 Ada Generation →