A data center GPU against a consumer card, one Blackwell and one Ada Lovelace: up to 192 GB HBM3e against 12 GB GDDR6X, 16x the memory bandwidth on the B100, and NVLink 1,800 GB/s on the B100 where the RTX 4070 Ti is PCIe only.

At a glance

Updated 5 minutes ago
Memory
192 GB
HBM3e
Memory bandwidth
8.00 TB/s
From
--
Memory
12 GB
GDDR6X
Memory bandwidth
504 GB/s
From
$0.19 /GPU/hr
2 providers

Price comparison

Cheapest listed price per GPU per hour by billing type, and the median across providers.

Billing B100 RTX 4070 Ti Difference
On-demand -- $0.19
Spot No spot listings $0.08
Median -- $0.21

Median: Median across providers, one vote each, so a large catalog does not outweigh a small one.

Price history

B100 vs RTX 4070 Ti price history

Weekly median on-demand price per GPU per hour

Last 12 months
Aggregating historical prices...

Specs comparison

Spec B100 RTX 4070 Ti Difference
Memory
Capacity 192 GB HBM3e 12 GB GDDR6X 16x more on B100
Bandwidth 8,000 GB/s 504 GB/s 16x higher on B100
Bus width 192-bit
Compute · dense
FP4 7,000 TFLOPS Not supported B100 only
FP8 3,500 TFLOPS 160.4 TFLOPS 22x higher on B100
FP16 / BF16 1,750 TFLOPS 80.2 TFLOPS 22x higher on B100
INT8 3,500 TOPS 320.7 TOPS 11x higher on B100
FP32 60 TFLOPS 40.1 TFLOPS 1.5x higher on B100
FP64 30 TFLOPS Not supported B100 only
Platform
Interconnect NVLink 1,800 GB/s PCIe only NVLink on B100 only
Released Q4 2024 Q1 2023 2 years newer on B100
Precision
Supported formats FP4FP6FP8FP16BF16TF32FP32FP64INT8 FP8FP16BF16TF32FP32INT4INT8

Compute: Vendor peak figures, dense and per GPU. Not measured throughput.

Source: B100 datasheet and RTX 4070 Ti 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 4070 Ti /GPU/hr
Runpod logo Runpod -- On-Demand $0.19
Salad logo Salad -- On-Demand $0.24

Similar GPUs

Other comparisons in the same class.

Our data for Nvidia B100 was last updated on Sept. 7, 2026, and for Nvidia RTX 4070 Ti on Sept. 7, 2026.