GPU comparison
MI355X vs MI350X
Same chip family, same 288 GB of HBM3E at 8 TB/s. MI355X runs at up to 1,400 W with liquid cooling for about 9% more FP8; MI350X is air-cooled at 1,000 W and cheaper per month. Memory-bound workloads see little difference; compute-bound training benefits from MI355X.
- Updated Nov 4, 2026
- Specs: vendor datasheets, dense Tensor figures
- Prices: live CoreGPU catalog
| Spec | AMD Instinct MI355X | AMD Instinct MI350X |
|---|---|---|
| Architecture | CDNA 4 | CDNA 4 |
| GPU memory | 288 GB HBM3E | 288 GB HBM3E |
| Memory bandwidth | 8 TB/s | 8 TB/s |
| FP8 dense | 5 PF | 4.6 PF |
| FP4 dense | 10.1 PF | 9.2 PF |
| Interconnect | Infinity Fabric · 1.08 TB/s | Infinity Fabric · 1.08 TB/s |
| Power (TDP) | 1,400 W | 1,000 W |
| Price per GPU / month | $2,449 | $2,249 |
| Price per GB of memory | $8.50 | $7.81 |
| Price per FP8 PFLOPS | $490 | $489 |
| Availability | 21 available | Only 6 left |
Green marks the better value on each line. Prices are per GPU per month at CoreGPU, at least 25% below the market median.
- Compute-bound training and fine-tuning
- Maximum FP8 and FP4 throughput on CDNA 4
$2,449 /GPU/moConfigure MI355X
- Memory-bound inference at a lower price
- The most GPU memory per dollar we offer
$2,249 /GPU/moConfigure MI350X