A data center GPU against a consumer card, one Blackwell and one Ampere: 180 GB HBM3e against 24 GB GDDR6X and 8.2x the memory bandwidth on the B200.
At a glance
Updated 6 minutes ago- Memory
- 180 GB
- HBM3e
- Memory bandwidth
- 7.70 TB/s
- From
- $3.75 /GPU/hr
- 35 providers
- Memory
- 24 GB
- GDDR6X
- Memory bandwidth
- 936 GB/s
- From
- $0.10 /GPU/hr
- 8 providers
Price comparison
Cheapest listed price per GPU per hour by billing type, and the median across providers.
| Billing | B200 | RTX 3090 | Difference |
|---|---|---|---|
| On-demand | $3.75 | $0.10 | 38x more expensive on B200 |
| Spot | $3.12 | $0.09 | 35x more expensive on B200 |
| Reserved | $3.75 | $0.06 | 62x more expensive on B200 |
| Median | $6.39 | $0.31 | 21x more expensive on B200 |
Median: Median across providers, one vote each, so a large catalog does not outweigh a small one.
Price history
B200 vs RTX 3090 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | B200 | RTX 3090 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 180 GB HBM3e | 24 GB GDDR6X | 7.5x more on B200 |
| Bandwidth | 7,700 GB/s | 936 GB/s | 8.2x higher on B200 |
| Bus width | 384-bit | ||
| Compute · dense | |||
| FP4 | 9,000 TFLOPS | Not supported | B200 only |
| FP8 | 4,500 TFLOPS | Not supported | B200 only |
| FP16 / BF16 | 2,250 TFLOPS | 71.2 TFLOPS | 32x higher on B200 |
| INT8 | 4,500 TOPS | 284.7 TOPS | 16x higher on B200 |
| FP32 | 75 TFLOPS | 35.6 TFLOPS | 2.1x higher on B200 |
| FP64 | 37 TFLOPS | Not supported | B200 only |
| Platform | |||
| Interconnect | NVLink 1,800 GB/s | NVLink 112 GB/s | 16x higher on B200 |
| Board power | 1,000 W | 350 W | 2.9x higher on B200 |
| Released | Q1 2024 | Q3 2020 | 4 years newer on B200 |
| Precision | |||
| Supported formats | FP4FP6FP8FP16BF16TF32FP32FP64INT8 | FP16BF16TF32FP32INT4INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: B200 datasheet and RTX 3090 datasheet.
Where to rent them
Providers listing these GPUs, those with both first, so you can switch without moving clouds.
| Provider | B200 /GPU/hr | RTX 3090 /GPU/hr |
|---|---|---|
GPU.ai
|
On-Demand $5.40 | On-Demand $0.22 |
EmpirioLabs AI
|
On-Demand $9.00 | On-Demand $0.40 |
Packet·ai
|
On-Demand $3.75 | -- |
Lium
|
On-Demand $5.50 | -- |
Vast.ai
|
On-Demand $6.88 | -- |
Spheron
|
On-Demand $7.20 | -- |
Oblivus
|
On-Demand $8.40 | -- |
Verda
|
Spot $3.12 | -- |
HyperAI
|
-- | On-Demand $0.10 |
Theta EdgeCloud
|
-- | On-Demand $0.13 |
Salad
|
-- | On-Demand $0.25 |
SwissGPU
|
-- | On-Demand $0.31 |
TensorDock
|
-- | On-Demand $0.31 |
Runpod
|
-- | Reservation on request |
35 providers list the B200 and 8 the RTX 3090. Every listing is on the B200 page and the RTX 3090 page.
Similar GPUs
Other comparisons in the same class.
Our data for Nvidia B200 was last updated on Sept. 7, 2026, and for Nvidia RTX 3090 on Sept. 7, 2026.