GPU comparison
MI355X vs B300
Both carry 288 GB of HBM at 8 TB/s. MI355X has more dense FP8 (5.0 vs 4.5 PF), keeps strong FP64 and costs about half as much per month; B300 leads on FP4 (13.5 vs 10.1 PF) and runs every CUDA-only kernel. If your stack runs on ROCm, MI355X is the value pick.
- Updated Nov 4, 2026
- Specs: vendor datasheets, dense Tensor figures
- Prices: live CoreGPU catalog
| Spec | AMD Instinct MI355X | NVIDIA HGX B300 |
|---|---|---|
| Architecture | CDNA 4 | Blackwell Ultra |
| GPU memory | 288 GB HBM3E | 288 GB HBM3e |
| Memory bandwidth | 8 TB/s | 8 TB/s |
| FP8 dense | 5 PF | 4.5 PF |
| FP4 dense | 10.1 PF | 13.5 PF |
| Interconnect | Infinity Fabric · 1.08 TB/s | NVLink 5 · 1.8 TB/s |
| Power (TDP) | 1,400 W | 1,100 W |
| Price per GPU / month | $2,449 | $4,899 |
| Price per GB of memory | $8.50 | $17.01 |
| Price per FP8 PFLOPS | $490 | $1,089 |
| Availability | 21 available | Only 9 left |
Green marks the better value on each line. Prices are per GPU per month at CoreGPU, at least 25% below the market median.
- ROCm-ready stacks: PyTorch, JAX, vLLM, SGLang
- FP8 training and FP64 science
- The best price for 288 GB per GPU at this performance
$2,449 /GPU/moConfigure MI355X
- CUDA-only kernels and TensorRT-LLM
- Maximum FP4 inference throughput
- Teams standardised on NVIDIA tooling
$4,899 /GPU/moConfigure B300