A data center GPU against a consumer card, one Ampere and one Turing: 80 GB HBM2e against 4 GB GDDR5, 15x the memory bandwidth on the A100, and NVLink 600 GB/s on the A100 where the GTX 1650 is PCIe only.
At a glance
Updated 7 minutes ago- Memory
- 80 GB
- HBM2e · 40 GB on SXM, PCIe
- Memory bandwidth
- 1.94 TB/s
- 2,039 GB/s on SXM · 1,555 GB/s on SXM, PCIe
- From
- $0.89 /GPU/hr
- 43 providers
- Memory
- 4 GB
- GDDR5
- Memory bandwidth
- 128 GB/s
- From
- $0.02 /GPU/hr
- 2 providers
Price comparison
Cheapest listed price per GPU per hour by billing type, and the median across providers.
| Billing | A100 | GTX 1650 | Difference |
|---|---|---|---|
| On-demand | $0.89 | $0.02 | 44x more expensive on A100 |
| Spot | $0.68 | $0.01 | 45x more expensive on A100 |
| Reserved | $0.56 | $0.14 | 4.1x more expensive on A100 |
| Median | $1.81 | $0.02 | 91x more expensive on A100 |
Median: Median across providers, one vote each, so a large catalog does not outweigh a small one.
Price history
A100 vs GTX 1650 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | A100 | GTX 1650 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 80 GB HBM2e 40 GB on SXM, PCIe | 4 GB GDDR5 | 20x more on A100 |
| Bandwidth | 1,935 GB/s 2,039 GB/s on SXM 1,555 GB/s on SXM, PCIe | 128 GB/s | 15x higher on A100 |
| Bus width | 5,120-bit | 128-bit | 40x wider on A100 |
| Compute · dense | |||
| FP16 / BF16 | 312 TFLOPS | 6.0 TFLOPS | 52x higher on A100 |
| INT8 | 624 TOPS | Not supported | A100 only |
| FP32 | 19.5 TFLOPS | 3.0 TFLOPS | 6.5x higher on A100 |
| FP64 | 9.7 TFLOPS | Not supported | A100 only |
| Platform | |||
| Interconnect | NVLink 600 GB/s | PCIe only | NVLink on A100 only |
| Board power | 300 W | 75 W | 4x higher on A100 |
| Released | Q2 2020 | Q2 2019 | 13 months newer on A100 |
| Precision | |||
| Supported formats | FP16BF16TF32FP32FP64INT4INT8 | FP16FP32 | |
Figures are for each model's headline configuration. Where a form factor carries a different number, it is named under the figure.
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: A100 datasheet and GTX 1650 datasheet.
Where to rent them
Providers listing these GPUs, those with both first, so you can switch without moving clouds.
| Provider | A100 /GPU/hr | GTX 1650 /GPU/hr |
|---|---|---|
GPU.ai
|
On-Demand $0.89 | -- |
Vast.ai
|
On-Demand $0.91 | -- |
Thunder Compute
|
On-Demand $1.09 | -- |
Massed Compute
|
On-Demand $1.35 | -- |
Runpod
|
On-Demand $1.39 | -- |
Packet·ai
|
On-Demand $1.43 | -- |
Spheron
|
On-Demand $1.43 | -- |
Oblivus
|
On-Demand $1.47 | -- |
Salad
|
-- | On-Demand $0.0200 |
Database Mart
|
-- | Reserved (24mo) $0.14 |
43 providers list the A100 and 2 the GTX 1650. Every listing is on the A100 page and the GTX 1650 page.
Similar GPUs
Other comparisons in the same class.
Our data for Nvidia A100 was last updated on Sept. 7, 2026, and for Nvidia GTX 1650 on Sept. 7, 2026.