Kovara
Loading your page…
You can continue using the navigation while this page loads.
You can continue using the navigation while this page loads.
B300 SXM has 1100% more memory than L4 24GB (288 GB vs 24 GB). Its memory bandwidth is 2567% more (8 vs 0.3 TB/s). In the cloud, the median on-demand B300 SXM price is $7.45 per GPU-hour against $0.44 for the L4 24GB. Per gigabyte of GPU memory, that is $0.026 vs $0.018 per hour.
Manufacturer figures as recorded by Kovara. Higher memory and bandwidth are highlighted; neither is a benchmark of your workload.
| B300 SXM | L4 24GB | |
|---|---|---|
| Manufacturer | NVIDIA | NVIDIA |
| Architecture | Blackwell Ultra | Ada Lovelace |
| Memory | 288 GB HBM3E | 24 GB GDDR6 |
| Memory bandwidth | 8 TB/s | 0.3 TB/s |
| Power (TDP) | 1400 W | 72 W |
| Form factor | SXM | PCIe low-profile single-slot |
Public offers Kovara tracks, normalised to US dollars per GPU-hour. Prices use on-demand terms where available; spot and reserved offers are on each GPU’s price pages. Lower is highlighted.
| B300 SXM | L4 24GB | |
|---|---|---|
| Lowest price | $6.60 | $0.44 |
| Median price | $7.45 | $0.44 |
| Highest price | $8.29 | $0.57 |
| Median per GB of memory | $0.026 | $0.018 |
| Public offers (all terms) | 28 | 7 |
| Providers | 11 | 3 |
Lowest tracked price per provider. Open a provider to see every offer, region and term.
Right now the cheapest on-demand B300 SXM Kovara tracks is $6.60 per GPU-hour and the cheapest L4 24GB is $0.44. Medians are $7.45 and $0.44. The cheaper GPU per hour is not always cheaper per job: a faster or larger GPU can finish sooner or need fewer units.
The B300 SXM has more memory: 288 GB against 24 GB. Memory decides which models and batch sizes fit on one GPU.
No. This page compares manufacturer specifications and public prices. Real performance depends on the model, precision, software and interconnect. Kova can help you estimate cost for a specific workload.