A data center GPU against a consumer card, one Grace Blackwell and one Ada Lovelace: 186 GB HBM3e against 16 GB GDDR6X, 12x the memory bandwidth on the GB200, and NVLink 1,800 GB/s on the GB200 where the RTX 4070 Ti Super is PCIe only.
At a glance
Updated 6 minutes ago- Memory
- 186 GB
- HBM3e
- Memory bandwidth
- 8.00 TB/s
- From
- $10.50 /GPU/hr
- 8 providers
- Memory
- 16 GB
- GDDR6X
- Memory bandwidth
- 672 GB/s
- From
- $0.12 /GPU/hr
- 3 providers
Price comparison
Cheapest listed price per GPU per hour by billing type, and the median across providers.
| Billing | GB200 | RTX 4070 Ti Super | Difference |
|---|---|---|---|
| On-demand | $10.50 | $0.12 | 84x more expensive on GB200 |
| Spot | $27.04 | $0.09 | 300x more expensive on GB200 |
| Reserved | $10.58 | No reserved listings | |
| Median | $16.00 | $0.26 | 62x more expensive on GB200 |
Median: Median across providers, one vote each, so a large catalog does not outweigh a small one.
Price history
GB200 vs RTX 4070 Ti Super price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | GB200 | RTX 4070 Ti Super | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 186 GB HBM3e | 16 GB GDDR6X | 12x more on GB200 |
| Bandwidth | 8,000 GB/s | 672 GB/s | 12x higher on GB200 |
| Bus width | 256-bit | ||
| Compute · dense | |||
| FP4 | 10,000 TFLOPS | Not supported | GB200 only |
| FP8 | 5,000 TFLOPS | 176.4 TFLOPS | 28x higher on GB200 |
| FP16 / BF16 | 2,500 TFLOPS | 88.2 TFLOPS | 28x higher on GB200 |
| INT8 | 5,000 TOPS | 352.8 TOPS | 14x higher on GB200 |
| FP32 | 80 TFLOPS | 44.1 TFLOPS | 1.8x higher on GB200 |
| FP64 | 40 TFLOPS | Not supported | GB200 only |
| Platform | |||
| Interconnect | NVLink 1,800 GB/s | PCIe only | NVLink on GB200 only |
| Board power | 1,200 W | 285 W | 4.2x higher on GB200 |
| Released | Q1 2024 | Q1 2024 | |
| Precision | |||
| Supported formats | FP4FP6FP8FP16BF16TF32FP32FP64INT8 | FP8FP16BF16TF32FP32INT4INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: GB200 datasheet and RTX 4070 Ti Super datasheet.
Where to rent them
Providers listing these GPUs, those with both first, so you can switch without moving clouds.
| Provider | GB200 /GPU/hr | RTX 4070 Ti Super /GPU/hr |
|---|---|---|
CoreWeave
|
On-Demand $10.50 | -- |
Oracle Cloud
|
On-Demand $16.00 | -- |
Azure
|
On-Demand $27.04 | -- |
AWS
|
Reservation $10.58 | -- |
CUDO
|
Custom on request | -- |
Canopy Wave
|
Custom on request | -- |
Nebius
|
Custom on request | -- |
Together AI
|
Custom on request | -- |
Vast.ai
|
-- | On-Demand $0.12 |
Salad
|
-- | On-Demand $0.26 |
Theta EdgeCloud
|
-- | On-Demand $0.46 |
Similar GPUs
Other comparisons in the same class.
Our data for Nvidia GB200 was last updated on Sept. 7, 2026, and for Nvidia RTX 4070 Ti Super on Sept. 7, 2026.