The B300 has 9x the memory and 4.5x the bandwidth. The RTX 5090 is typically cheaper.
At a glance
Memory
9x more on B300
- B300
- 288 GB
- RTX 5090
- 32 GB
Memory bandwidth
4.5x higher on B300
- B300
- 8.00 TB/s
- RTX 5090
- 1.79 TB/s
Cheapest on-demand
93% cheaper on RTX 5090
- B300
- $4.99 /GPU/hr
- RTX 5090
- $0.35 /GPU/hr
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | B300 | RTX 5090 | Difference |
|---|---|---|---|
| On-demand | $8.99 /GPU/hr from $4.99 | $0.72 /GPU/hr from $0.35 | 92% cheaper on RTX 5090 |
| Reserved | $5.31 /GPU/hr from $4.25 | $0.60 /GPU/hr from $0.21 (1 mo) | 89% cheaper on RTX 5090 |
| Spot | $5.72 /GPU/hr from $4.08 | -- /GPU/hr from $0.25 |
Heads up: A provider's own page may quote a different figure, for example on tax, region or a promotion. A monthly-only plan shows a derived hourly rate. Medians are across providers, one vote each, so a large catalog does not outweigh a small one. No median for spot on the RTX 5090: we only show one when at least 3 providers list the GPU on that billing type. Verify before provisioning. More on how we price.
Price history
B300 vs RTX 5090 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | B300 | RTX 5090 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 288 GB HBM3e | 32 GB GDDR7 | 9x more on B300 |
| Bandwidth | 8,000 GB/s | 1,792 GB/s | 4.5x higher on B300 |
| Bus width | 8,192-bit | 512-bit | 16x wider on B300 |
| Compute · dense | |||
| FP4 | 14,000 TFLOPS | 1,676 TFLOPS | 8.4x higher on B300 |
| FP8 | 4,500 TFLOPS | 419 TFLOPS | 11x higher on B300 |
| FP16 / BF16 | 2,250 TFLOPS | 209.5 TFLOPS | 11x higher on B300 |
| INT8 | 153.5 TOPS | 838 TOPS | 5.5x higher on RTX 5090 |
| FP32 | 75 TFLOPS | 104.8 TFLOPS | 40% higher on RTX 5090 |
| FP64 | 1.2 TFLOPS | Not supported | B300 only |
| Platform | |||
| Interconnect | NVLink 1,800 GB/s | PCIe only | NVLink on B300 only |
| Board power | 1,100 W | 575 W | 91% higher on B300 |
| Released | Q1 2025 | Q1 2025 | |
| Precision | |||
| Supported formats | FP4FP6FP8FP16BF16TF32FP32FP64INT8 | FP4FP8FP16BF16TF32FP32INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: B300 datasheet and RTX 5090 datasheet.
Where to rent them
Providers that rent these GPUs, with each one's cheapest rate. Providers that rent both are listed first.
| Provider | B300 | RTX 5090 |
|---|---|---|
Lium
Distributed
|
$8.75 /GPU/hr On-demand SXM | $0.69 /GPU/hr On-demand |
Sesterce
France
|
$8.80 /GPU/hr On-demand | $0.71 /GPU/hr On-demand |
GPU.ai
UAE
|
$8.99 /GPU/hr On-demand SXM | $0.53 /GPU/hr On-demand |
Runpod
USA
|
$8.99 /GPU/hr On-demand SXM | $0.69 /GPU/hr On-demand |
Runcrate
USA
|
$10.40 /GPU/hr On-demand NVL | $0.85 /GPU/hr On-demand PCIe |
Daytona
USA
|
$7.10 /GPU/hr On-demand | -- |
Spheron
Singapore
|
$12.41 /GPU/hr On-demand SXM | -- |
EmpirioLabs AI
USA
|
$16.00 /GPU/hr On-demand | -- |
HyperAI
Hong Kong
|
-- | $0.35 /GPU/hr On-demand |
Salad
Distributed
|
-- | $0.50 /GPU/hr On-demand |
Theta EdgeCloud
Distributed
|
-- | $0.65 /GPU/hr On-demand |
35 providers list the B300 and 21 the RTX 5090. Every listing is on the B300 page and the RTX 5090 page.
Similar GPUs
Other comparisons in the same class.
-
-
-
-
-
Nvidia RTX 4090
24 GB GDDR6X · 44% less bandwidth than the RTX 5090
On-demand from $0.33 /GPU/hr
Our data for Nvidia B300 was last updated on Sept. 14, 2026, and for Nvidia RTX 5090 on Sept. 14, 2026.