GPU comparison
B300 vs MI355X: specs and rental prices
NVIDIA B300 against AMD Instinct MI355X: 270 GB against 288 GB of memory, lowest listed on-demand price $7.40 against $8.60 per GPU-hour. Specs from NVIDIA and AMD, prices as of Oct 25, 2026.
In short
- The MI355X lists 288 GB of GPU memory against 270 GB for the B300: 1.07× higher.
- Memory type is HBM3E on the B300 and HBM3E on the MI355X.
- The MI355X lists 8,000 GB/s of memory bandwidth against 7,700 GB/s for the B300: 1.04× higher.
- The MI355X lists 5,000 TFLOPS of FP16 / BF16 tensor throughput against 4,500 TFLOPS for the B300: 1.11× higher.
- Maximum power is listed at 1,100 W for the B300 and 1,400 W for the MI355X.
- Not every figure can be compared: at least one vendor page does not publish: TF32 tensor throughput; GPU-to-GPU interconnect.
- The lowest listed on-demand price is $7.40 per GPU-hour for the B300 (Hyperstack) and $8.60 for the MI355X (Oracle Cloud).
- Per GB of GPU memory that is $0.027 per hour for the B300 and $0.030 for the MI355X.
This summary is generated from the tables below. Prices were last checked Oct 25, 2026. A listing not re-checked for 7 days is greyed and left out of every lowest-price figure; after 14 days it is removed from the page.
Specifications side by side
| Specification | B300, per GPU (HGX B300) | MI355X | Difference |
|---|---|---|---|
| GPU memory | 270 GB | 288 GB | MI355X 1.07× higher |
| Memory type | HBM3E | HBM3E | Same |
| Memory bandwidth | 7,700 GB/s | 8,000 GB/s | MI355X 1.04× higher |
| FP8 tensor throughput, with sparsity | 9,000 TFLOPS | 10,100 TFLOPS | MI355X 1.12× higher |
| FP16 / BF16 tensor throughput, with sparsity | 4,500 TFLOPS | 5,000 TFLOPS | MI355X 1.11× higher |
| TF32 tensor throughput | 2,200 TFLOPS (with sparsity) | Not published | — |
| FP64 throughput | 1.2 TFLOPS | 78.6 TFLOPS | MI355X 65.5× higher |
| Maximum power | 1,100 W | 1,400 W | MI355X 1.27× higher |
| GPU-to-GPU interconnect | 1,800 GB/s | Not published | — |
Compared versions: B300, per GPU (HGX B300) and MI355X. The figure in the stronger cell is shaded; power is shown without a winner. Two throughput figures are compared only when both vendors state them on the same basis (both with sparsity, or both dense), and “derived” means a total the vendor publishes divided by the GPU count it publishes. Full tables with sources: B300 specifications · MI355X specifications.
Rental prices
| Rental price | B300 | MI355X | Difference |
|---|---|---|---|
| Lowest listed on-demand price | $7.40 per GPU-hour · Hyperstack · checked Oct 25, 2026 | $8.60 per GPU-hour · Oracle Cloud · checked Oct 25, 2026 | MI355X 1.16× higher |
| Lowest listed spot price | $0.99 per GPU-hour · Nebius · checked Oct 25, 2026 | $2.97 per GPU-hour · DigitalOcean · checked Oct 25, 2026 | MI355X 3× higher |
| Price per GB of memory | $0.027 per GB of GPU memory per hour | $0.030 per GB of GPU memory per hour | MI355X 1.09× higher |
| Fresh listings | 13 from 10 providers | 2 from 2 providers | — |
Prices cover every version and instance size the providers list, so they are not tied to the versions compared above; the price per GB of memory divides the lowest fresh on-demand price by the memory of the compared version. Listed prices are not like for like across providers. See every listing: B300 prices · MI355X prices.
More on these GPUs
Cite this page
Last updated Oct 25, 2026. Figures may change as records are updated — include the date you retrieved them.
| APA | Data Center Census. (2026). B300 vs MI355X. Retrieved from https://datacentercensus.com/gpu-prices/compare/b300-vs-mi355x |
|---|---|
| MLA | “B300 vs MI355X.” Data Center Census, Oct 25, 2026, https://datacentercensus.com/gpu-prices/compare/b300-vs-mi355x. |
| Link | https://datacentercensus.com/gpu-prices/compare/b300-vs-mi355x |
Republishing a figure or table? Attribute it to Data Center Census with a link to this page. The underlying data is downloadable as JSON and CSV; the press kit has standing figures and contact details.