GPU comparison
Vera Rubin vs B300: specs and rental prices
NVIDIA Vera Rubin (Rubin GPU) against NVIDIA B300: 288 GB against 270 GB of memory. Specs from NVIDIA, prices as of Oct 29, 2026.
In short
- The Vera Rubin lists 288 GB of GPU memory against 270 GB for the B300: 1.07× higher.
- Memory type is HBM4 on the Vera Rubin and HBM3E on the B300.
- The Vera Rubin lists 19,200 GB/s of memory bandwidth against 7,700 GB/s for the B300: 2.49× higher.
- Not every figure can be compared: at least one vendor page does not publish: Maximum power.
- Only the B300 has a fresh on-demand listing ($7.40 per GPU-hour at Hyperstack); the Vera Rubin has none right now.
This summary is generated from the tables below. Prices were last checked Oct 29, 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 | Vera Rubin Rubin GPU | B300, per GPU (HGX B300) | Difference |
|---|---|---|---|
| GPU memory | 288 GB | 270 GB | Vera Rubin 1.07× higher |
| Memory type | HBM4 | HBM3E | Different |
| Memory bandwidth | 19,200 GB/s | 7,700 GB/s | Vera Rubin 2.49× higher |
| FP8 tensor throughput | 17,500 TFLOPS (dense) | 9,000 TFLOPS (with sparsity) | Not compared: the vendors state the figures on different bases |
| FP16 / BF16 tensor throughput | 4,000 TFLOPS (dense) | 4,500 TFLOPS (with sparsity) | Not compared: the vendors state the figures on different bases |
| TF32 tensor throughput | 2,000 TFLOPS (dense) | 2,200 TFLOPS (with sparsity) | Not compared: the vendors state the figures on different bases |
| FP64 throughput | 33 TFLOPS | 1.2 TFLOPS | Vera Rubin 27.5× higher |
| Maximum power | Not published | 1,100 W | — |
| GPU-to-GPU interconnect | 3,000 GB/s | 1,800 GB/s | Vera Rubin 1.67× higher |
Compared versions: Vera Rubin Rubin GPU and B300, per GPU (HGX B300). 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: Vera Rubin specifications · B300 specifications.
Rental prices
| Rental price | Vera Rubin | B300 | Difference |
|---|---|---|---|
| Lowest listed on-demand price | No fresh listing | $7.40 per GPU-hour · Hyperstack · checked Oct 29, 2026 | — |
| Lowest listed spot price | No fresh listing | $0.99 per GPU-hour · Nebius · checked Oct 29, 2026 | — |
| Price per GB of memory | Not available | $0.027 per GB of GPU memory per hour | — |
| Fresh listings | 0 from 0 providers | 13 from 10 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: Vera Rubin prices · B300 prices.
More on these GPUs
Cite this page
Last updated Oct 29, 2026. Figures may change as records are updated — include the date you retrieved them.
| APA | Data Center Census. (2026). Vera Rubin vs B300. Retrieved from https://datacentercensus.com/gpu-prices/compare/vera-rubin-vs-b300 |
|---|---|
| MLA | “Vera Rubin vs B300.” Data Center Census, Oct 29, 2026, https://datacentercensus.com/gpu-prices/compare/vera-rubin-vs-b300. |
| Link | https://datacentercensus.com/gpu-prices/compare/vera-rubin-vs-b300 |
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.