A data center GPU against a consumer card, one Blackwell Ultra and one Ada Lovelace: up to 288 GB HBM3e against 24 GB GDDR6X, 7.9x the memory bandwidth on the B300, and NVLink 1,800 GB/s on the B300 where the RTX 4090 is PCIe only.
At a glance
Updated 6 minutes ago- Memory
- 288 GB
- HBM3e
- Memory bandwidth
- 8.00 TB/s
- From
- $6.50 /GPU/hr
- 30 providers
- Memory
- 24 GB
- GDDR6X
- Memory bandwidth
- 1.01 TB/s
- From
- $0.23 /GPU/hr
- 19 providers
Price comparison
Cheapest listed price per GPU per hour by billing type, and the median across providers.
| Billing | B300 | RTX 4090 | Difference |
|---|---|---|---|
| On-demand | $6.50 | $0.23 | 28x more expensive on B300 |
| Spot | $2.99 | $0.15 | 20x more expensive on B300 |
| Reserved | $4.25 | $0.27 | 16x more expensive on B300 |
| Median | $7.87 | $0.44 | 18x more expensive on B300 |
Median: Median across providers, one vote each, so a large catalog does not outweigh a small one.
Price history
B300 vs RTX 4090 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | B300 | RTX 4090 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 288 GB HBM3e | 24 GB GDDR6X | 12x more on B300 |
| Bandwidth | 8,000 GB/s | 1,010 GB/s | 7.9x higher on B300 |
| Bus width | 8,192-bit | 384-bit | 21x wider on B300 |
| Compute · dense | |||
| FP4 | 14,000 TFLOPS | Not supported | B300 only |
| FP8 | 4,500 TFLOPS | 330.3 TFLOPS | 14x higher on B300 |
| FP16 / BF16 | 2,250 TFLOPS | 165.2 TFLOPS | 14x higher on B300 |
| INT8 | 153.5 TOPS | 660.6 TOPS | 4.3x higher on RTX 4090 |
| FP32 | 75 TFLOPS | 82.6 TFLOPS | 1.1x higher on RTX 4090 |
| 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 | 450 W | 2.4x higher on B300 |
| Released | Q1 2025 | Q4 2022 | 2 years newer on B300 |
| Precision | |||
| Supported formats | FP4FP6FP8FP16BF16TF32FP32FP64INT8 | FP8FP16BF16TF32FP32INT4INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: B300 datasheet and RTX 4090 datasheet.
Where to rent them
Providers listing these GPUs, those with both first, so you can switch without moving clouds.
| Provider | B300 /GPU/hr | RTX 4090 /GPU/hr |
|---|---|---|
GPU.ai
|
On-Demand $7.89 | On-Demand $0.33 |
Runpod
|
On-Demand $7.89 | On-Demand $0.34 |
Packet·ai
|
Custom on request | On-Demand $0.39 |
Lyceum
|
On-Demand $7.99 | -- |
GPUaaS
|
Custom on request | -- |
Impossible Cloud
|
Reserved (60mo) $4.32 | -- |
Canopy Wave
|
Custom on request | -- |
Bentaus
|
On-Demand $6.50 | -- |
Theta EdgeCloud
|
-- | On-Demand $0.23 |
Lium
|
-- | On-Demand $0.30 |
Salad
|
-- | On-Demand $0.30 |
Novita
|
-- | On-Demand $0.33 |
Vast.ai
|
-- | On-Demand $0.38 |
30 providers list the B300 and 19 the RTX 4090. Every listing is on the B300 page and the RTX 4090 page.
Similar GPUs
Other comparisons in the same class.
Our data for Nvidia B300 was last updated on Sept. 7, 2026, and for Nvidia RTX 4090 on Sept. 7, 2026.