Two Nvidia data center GPUs, one Blackwell Ultra and one Hopper: 288 GB HBM3e against 80 GB HBM3 and 2.4x the memory bandwidth on the B300.
At a glance
Memory
- B300
- 288 GB
- H100
- 80 GB
3.6x more on B300
Memory bandwidth
- B300
- 8.00 TB/s
- H100
- 3.35 TB/s
2.4x higher on B300
Cheapest on-demand
- B300
- $6.50 /GPU/hr
- H100
- $1.41 /GPU/hr
4.6x more expensive on B300
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | B300 | H100 | Difference |
|---|---|---|---|
| On-demand | $7.89 /GPU/hr from $6.50 | $3.29 /GPU/hr from $1.41 | 2.4x more expensive on B300 |
| Reserved | $5.71 /GPU/hr from $4.25 | $3.11 /GPU/hr from $1.53 (1 mo) | 45% cheaper on H100 |
| Spot | $4.48 /GPU/hr from $2.99 | $2.00 /GPU/hr from $0.35 | 2.2x more expensive on B300 |
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. Verify before provisioning. More on how we price.
Price history
B300 vs H100 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | B300 | H100 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 288 GB HBM3e | 80 GB HBM3 94 GB on NVL | 3.6x more on B300 |
| Bandwidth | 8,000 GB/s | 3,350 GB/s 2,000 GB/s on PCIe 3,938 GB/s on NVL | 2.4x higher on B300 |
| Bus width | 8,192-bit | 5,120-bit | 1.6x wider on B300 |
| Compute · dense | |||
| FP4 | 14,000 TFLOPS | Not supported | B300 only |
| FP8 | 4,500 TFLOPS | 1,979 TFLOPS | 2.3x higher on B300 |
| FP16 / BF16 | 2,250 TFLOPS | 989.5 TFLOPS | 2.3x higher on B300 |
| INT8 | 153.5 TOPS | 1,979 TOPS | 13x higher on H100 |
| FP32 | 75 TFLOPS | 67 TFLOPS | 1.1x higher on B300 |
| FP64 | 1.2 TFLOPS | 34 TFLOPS | 28x higher on H100 |
| Platform | |||
| Interconnect | NVLink 1,800 GB/s | NVLink 900 GB/s NVLink 600 GB/s on PCIe, NVL | 2x higher on B300 |
| Board power | 1,100 W | 700 W | 1.6x higher on B300 |
| Released | Q1 2025 | Q3 2022 | 2 years newer on B300 |
| Precision | |||
| Supported formats | FP4FP6FP8FP16BF16TF32FP32FP64INT8 | FP8FP16BF16TF32FP32FP64INT8 | |
Figures are for each model's headline configuration. Where a form factor carries a different number, it is named under the figure.
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: B300 datasheet and H100 datasheet.
Where to rent them
Providers listing these GPUs, those with both first, so you can switch without moving clouds.
| Provider | B300 /GPU/hr | H100 /GPU/hr |
|---|---|---|
GPU.ai
|
On-Demand $7.89 | On-Demand $1.98 |
Vast.ai
|
On-Demand $9.38 | On-Demand $1.73 |
Runpod
|
On-Demand $7.89 | -- |
Lyceum
|
On-Demand $7.99 | -- |
TheAI Cloud
|
Reserved (24mo) $4.90 | -- |
GPUaaS
|
Custom on request | -- |
Packet·ai
|
Custom on request | -- |
Impossible Cloud
|
Reserved (60mo) $4.32 | -- |
Lium
|
-- | On-Demand $1.41 |
HyperAI
|
-- | On-Demand $1.80 |
Koyeb
|
-- | On-Demand $2.50 |
Spheron
|
-- | On-Demand $2.64 |
Massed Compute
|
-- | On-Demand $2.73 |
Runcrate
|
-- | On-Demand $2.75 |
31 providers list the B300 and 53 the H100. Every listing is on the B300 page and the H100 page.
Similar GPUs
Other comparisons in the same class.
-
Nvidia B200
From $3.75 /GPU/hr Compare -
Nvidia H200
From $2.09 /GPU/hr Compare -
Nvidia GB300
From $18.00 /GPU/hr Compare -
Nvidia RTX 5090
From $0.35 /GPU/hr Compare
Our data for Nvidia B300 was last updated on Sept. 14, 2026, and for Nvidia H100 on Sept. 14, 2026.