A data center GPU against a workstation card, one Blackwell and one Turing: up to 192 GB HBM3e against 16 GB GDDR6 and 18x the memory bandwidth on the B100.
At a glance
Updated 9 hours ago- Memory
- 192 GB
- HBM3e
- Memory bandwidth
- 8.00 TB/s
- From
- --
- Memory
- 16 GB
- GDDR6
- Memory bandwidth
- 448 GB/s
- From
- $0.60 /GPU/hr
- 2 providers
Price comparison
Cheapest listed price per GPU per hour by billing type, and the median across providers.
| Billing | B100 | RTX 5000 | Difference |
|---|---|---|---|
| On-demand | -- | $0.60 | |
| Median | -- | $0.71 |
Median: Median across providers, one vote each, so a large catalog does not outweigh a small one.
Price history
B100 vs RTX 5000 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | B100 | RTX 5000 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 192 GB HBM3e | 16 GB GDDR6 | 12x more on B100 |
| Bandwidth | 8,000 GB/s | 448 GB/s | 18x higher on B100 |
| Bus width | 256-bit | ||
| Compute · dense | |||
| FP4 | 7,000 TFLOPS | Not supported | B100 only |
| FP8 | 3,500 TFLOPS | Not supported | B100 only |
| FP16 / BF16 | 1,750 TFLOPS | 89.2 TFLOPS | 20x higher on B100 |
| INT8 | 3,500 TOPS | 178.4 TOPS | 20x higher on B100 |
| FP32 | 60 TFLOPS | 11.2 TFLOPS | 5.4x higher on B100 |
| FP64 | 30 TFLOPS | Not supported | B100 only |
| Platform | |||
| Interconnect | NVLink 1,800 GB/s | NVLink 50 GB/s | 36x higher on B100 |
| Released | Q4 2024 | Q3 2018 | 6 years newer on B100 |
| Precision | |||
| Supported formats | FP4FP6FP8FP16BF16TF32FP32FP64INT8 | FP16FP32INT4INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: B100 datasheet and RTX 5000 datasheet.
Where to rent them
Providers listing these GPUs, those with both first, so you can switch without moving clouds.
| Provider | B100 /GPU/hr | RTX 5000 /GPU/hr |
|---|---|---|
OVH
|
-- | On-Demand $0.60 |
Paperspace
|
-- | On-Demand $0.82 |
Similar GPUs
Other comparisons in the same class.
Our data for Nvidia B100 was last updated on Sept. 7, 2026, and for Nvidia RTX 5000 on Sept. 7, 2026.