The L40 is newer, with 12x the memory and 6.8x the bandwidth. The GTX 1650 is cheaper right now.
At a glance
Memory
12x more on L40
- GTX 1650
- 4 GB
- L40
- 48 GB
Memory bandwidth
6.8x higher on L40
- GTX 1650
- 128 GB/s
- L40
- 864 GB/s
Cheapest on-demand
96% cheaper on GTX 1650
- GTX 1650
- $0.02 /GPU/hr
- L40
- $0.46 /GPU/hr
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | GTX 1650 | L40 | Difference |
|---|---|---|---|
| On-demand | -- /GPU/hr from $0.02 | $1.05 /GPU/hr from $0.46 | |
| Reserved | -- /GPU/hr from $0.09 (24 mo) | -- /GPU/hr from $0.70 | |
| Spot | -- /GPU/hr from $0.01 | $0.78 /GPU/hr from $0.40 |
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, reserved and spot on the GTX 1650 and reserved on the L40: 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
GTX 1650 vs L40 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | GTX 1650 | L40 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 4 GB GDDR5 | 48 GB GDDR6 | 12x more on L40 |
| Bandwidth | 128 GB/s | 864 GB/s | 6.8x higher on L40 |
| Bus width | 128-bit | 384-bit | 3x wider on L40 |
| Compute · dense | |||
| FP8 | Not supported | 362 TFLOPS | L40 only |
| FP16 / BF16 | 6.0 TFLOPS | 181.1 TFLOPS | 30x higher on L40 |
| INT8 | Not supported | 362 TOPS | L40 only |
| FP32 | 3.0 TFLOPS | 90.5 TFLOPS | 30x higher on L40 |
| Platform | |||
| Interconnect | PCIe only | PCIe only | |
| Board power | 75 W | 300 W | 4x higher on L40 |
| Released | Q2 2019 | Q4 2022 | 4 years newer on L40 |
| Precision | |||
| Supported formats | FP16FP32 | FP8FP16BF16TF32FP32INT4INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: GTX 1650 datasheet and L40 datasheet.
Where to rent them
Providers that rent these GPUs, with each one's cheapest rate. Providers that rent both are listed first.
| Provider | GTX 1650 | L40 |
|---|---|---|
Vast.ai
USA
|
$0.68 /GPU/hr On-demand | $0.46 /GPU/hr On-demand |
Salad
Distributed
|
$0.0200 /GPU/hr On-demand | -- |
Database Mart
USA
|
$0.09 /GPU/hr Reserved | -- |
GPU.ai
UAE
|
-- | $0.78 /GPU/hr On-demand |
Thunder Compute
USA
|
-- | $0.79 /GPU/hr On-demand |
Runpod
USA
|
-- | $0.82 /GPU/hr On-demand |
Massed Compute
USA
|
-- | $0.86 /GPU/hr On-demand |
Hyperstack
UK
|
-- | $1.00 /GPU/hr On-demand |
Oblivus
USA
|
-- | $1.05 /GPU/hr On-demand PCIe |
Spheron
Singapore
|
-- | $1.06 /GPU/hr On-demand PCIe |
3 providers list the GTX 1650 and 13 the L40. Every listing is on the GTX 1650 page and the L40 page.
Similar GPUs
Other comparisons in the same class.
-
Nvidia RTX 3060
12 GB GDDR6 · 2.8x the bandwidth of the GTX 1650
From $0.05 /GPU/hr Compare -
Nvidia RTX 3050
8 GB GDDR6 · 75% more bandwidth than the GTX 1650
From $0.07 /GPU/hr Compare
-
Nvidia GTX 1660
6 GB GDDR5 · 50% more bandwidth than the GTX 1650
From $0.04 /GPU/hr Compare
-
Nvidia A100
80 GB HBM2e · 2.2x the bandwidth of the L40
From $0.40 /GPU/hr Compare
-
Nvidia L40S
48 GB GDDR6 · released Q3 2023
From $0.55 /GPU/hr Compare
Our data for Nvidia GTX 1650 was last updated on Sept. 14, 2026, and for Nvidia L40 on Sept. 14, 2026.