The L40S is newer, with 4x the memory and 3.6x the bandwidth, and is cheaper right now.
At a glance
Memory
4x more on L40S
- K80
- 12 GB
- L40S
- 48 GB
Memory bandwidth
3.6x higher on L40S
- K80
- 240 GB/s
- L40S
- 864 GB/s
Cheapest on-demand
58% cheaper on L40S
- K80
- $0.90 /GPU/hr
- L40S
- $0.38 /GPU/hr
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | K80 | L40S | Difference |
|---|---|---|---|
| On-demand | -- /GPU/hr from $0.90 | $1.54 /GPU/hr from $0.38 | |
| Reserved | -- /GPU/hr from $0.04 (24 mo) | $1.10 /GPU/hr from $0.49 (6 mo) | |
| Spot | No spot listings | $0.98 /GPU/hr from $0.33 |
Heads up: A provider's own page may quote a different figure, for example on tax, region or a promotion. A monthly-only plan shows a derived hourly rate. Medians are across providers, one vote each, so a large catalog does not outweigh a small one. No median for on-demand and reserved on the K80: we only show one when at least 3 providers list the GPU on that billing type. Verify before provisioning. More on how we price.
Price history
K80 vs L40S price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | K80 | L40S | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 12 GB GDDR5 | 48 GB GDDR6 | 4x more on L40S |
| Bandwidth | 240 GB/s | 864 GB/s | 3.6x higher on L40S |
| Bus width | 384-bit | 384-bit | Identical |
| Compute · dense | |||
| FP8 | Not supported | 733 TFLOPS | L40S only |
| FP16 / BF16 | Not supported | 362.1 TFLOPS | L40S only |
| INT8 | Not supported | 733 TOPS | L40S only |
| FP32 | 4.4 TFLOPS | 91.6 TFLOPS | 21x higher on L40S |
| FP64 | 1.5 TFLOPS | Not supported | K80 only |
| Platform | |||
| Interconnect | PCIe only | PCIe only | |
| Board power | 150 W | 350 W | 2.3x higher on L40S |
| Released | Q4 2014 | Q3 2023 | 9 years newer on L40S |
| Precision | |||
| Supported formats | FP32FP64 | FP8FP16BF16TF32FP32INT4INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: K80 datasheet and L40S datasheet.
Where to rent them
Providers that rent these GPUs, with each one's cheapest rate. No provider we track offers both right now.
| Provider | K80 | L40S |
|---|---|---|
AWS
USA
|
$0.90 /GPU/hr On-demand | -- |
Database Mart
USA
|
$0.0447 /GPU/hr Reserved | -- |
Lium
Distributed
|
-- | $0.38 /GPU/hr On-demand PCIe |
Vast.ai
USA
|
-- | $0.54 /GPU/hr On-demand |
Novita
USA
|
-- | $0.55 /GPU/hr On-demand |
GPU.ai
UAE
|
-- | $0.79 /GPU/hr On-demand |
Runpod
USA
|
-- | $0.79 /GPU/hr On-demand |
EmpirioLabs AI
USA
|
-- | $0.80 /GPU/hr On-demand |
Packet·ai
USA
|
-- | $0.92 /GPU/hr On-demand |
Sesterce
France
|
-- | $0.97 /GPU/hr On-demand |
2 providers list the K80 and 40 the L40S. Every listing is on the K80 page and the L40S page.
Similar GPUs
Other comparisons in the same class.
-
Nvidia V100
32 GB HBM2 · 3.8x the bandwidth of the K80
From $0.11 /GPU/hr Compare -
Nvidia T4
16 GB GDDR6 · 25% more bandwidth than the K80
From $0.15 /GPU/hr Compare
-
Nvidia P100
16 GB HBM2 · 3x the bandwidth of the K80
From $0.10 /GPU/hr Compare
-
Nvidia H100
80 GB HBM3 · 3.9x the bandwidth of the L40S
From $1.30 /GPU/hr Compare
-
Nvidia A100
80 GB HBM2e · 2.2x the bandwidth of the L40S
From $0.34 /GPU/hr Compare
Our data for Nvidia K80 was last updated on Sept. 14, 2026, and for Nvidia L40S on Sept. 14, 2026.