Two Nvidia data center GPUs, one Blackwell and one Ada Lovelace: up to 192 GB HBM3e against 48 GB GDDR6, 9.3x the memory bandwidth on the B100, and NVLink 1,800 GB/s on the B100 where the L40S is PCIe only.
At a glance
Updated 7 minutes ago- Memory
- 192 GB
- HBM3e
- Memory bandwidth
- 8.00 TB/s
- From
- --
- Memory
- 48 GB
- GDDR6
- Memory bandwidth
- 864 GB/s
- From
- $0.38 /GPU/hr
- 36 providers
Price comparison
Cheapest listed price per GPU per hour by billing type, and the median across providers.
| Billing | B100 | L40S | Difference |
|---|---|---|---|
| On-demand | -- | $0.38 | |
| Spot | No spot listings | $0.40 | |
| Reserved | No reserved listings | $0.60 | |
| Median | -- | $1.28 |
Median: Median across providers, one vote each, so a large catalog does not outweigh a small one.
Price history
B100 vs L40S price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | B100 | L40S | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 192 GB HBM3e | 48 GB GDDR6 | 4x more on B100 |
| Bandwidth | 8,000 GB/s | 864 GB/s | 9.3x higher on B100 |
| Bus width | 384-bit | ||
| Compute · dense | |||
| FP4 | 7,000 TFLOPS | Not supported | B100 only |
| FP8 | 3,500 TFLOPS | 733 TFLOPS | 4.8x higher on B100 |
| FP16 / BF16 | 1,750 TFLOPS | 362.1 TFLOPS | 4.8x higher on B100 |
| INT8 | 3,500 TOPS | 733 TOPS | 4.8x higher on B100 |
| FP32 | 60 TFLOPS | 91.6 TFLOPS | 1.5x higher on L40S |
| FP64 | 30 TFLOPS | Not supported | B100 only |
| Platform | |||
| Interconnect | NVLink 1,800 GB/s | PCIe only | NVLink on B100 only |
| Released | Q4 2024 | Q3 2023 | 15 months newer on B100 |
| Precision | |||
| Supported formats | FP4FP6FP8FP16BF16TF32FP32FP64INT8 | FP8FP16BF16TF32FP32INT4INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: B100 datasheet and L40S datasheet.
Where to rent them
Providers listing these GPUs, those with both first, so you can switch without moving clouds.
| Provider | B100 /GPU/hr | L40S /GPU/hr |
|---|---|---|
Lium
|
-- | On-Demand $0.38 |
Novita
|
-- | On-Demand $0.55 |
Vast.ai
|
-- | On-Demand $0.74 |
EmpirioLabs AI
|
-- | On-Demand $0.80 |
GPU.ai
|
-- | On-Demand $0.80 |
Packet·ai
|
-- | On-Demand $0.92 |
Sesterce
|
-- | On-Demand $0.97 |
Massed Compute
|
-- | On-Demand $0.97 |
0 providers list the B100 and 36 the L40S. Every listing is on the B100 page and the L40S page.
Similar GPUs
Other comparisons in the same class.
Our data for Nvidia B100 was last updated on Sept. 7, 2026, and for Nvidia L40S on Sept. 7, 2026.