Two Nvidia workstation GPUs, one Ampere and one Pascal: 20 GB GDDR6 against 2 GB GDDR5 and 8x the memory bandwidth on the A4500.

At a glance

Memory

A4500
20 GB
P620
2 GB

10x more on A4500

Memory bandwidth

A4500
640 GB/s
P620
80 GB/s

8x higher on A4500

Cheapest on-demand

A4500
--
P620
--

Price comparison

Median price per GPU per hour by billing type, with the cheapest listing under it.

Billing A4500 P620 Difference
On-demand Sold out No on-demand listings
Reserved On request No reserved listings

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. Verify before provisioning. More on how we price.

Price history

A4500 vs P620 price history

Weekly median on-demand price per GPU per hour

Last 16 months
Aggregating historical prices...

Specs comparison

Spec A4500 P620 Difference
Memory
Capacity 20 GB GDDR6 2 GB GDDR5 10x more on A4500
Bandwidth 640 GB/s 80 GB/s 8x higher on A4500
Bus width 320-bit 128-bit 2.5x wider on A4500
Compute · dense
FP16 / BF16 94.6 TFLOPS
FP32 23.7 TFLOPS 1.3 TFLOPS 18x higher on A4500
Platform
Interconnect PCIe only PCIe only
Board power 200 W 40 W 5x higher on A4500
Released Q4 2021 Q1 2018 4 years newer on A4500
Precision
Supported formats FP16BF16TF32FP32INT4INT8 FP16FP32

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

Source: A4500 datasheet and P620 datasheet.

Where to rent them

Providers listing these GPUs, those with both first, so you can switch without moving clouds.

Provider A4500 /GPU/hr P620 /GPU/hr
Runpod logo Runpod Reservation on request --

Similar GPUs

Other comparisons in the same class.

Our data for Nvidia A4500 was last updated on Sept. 7, 2026, and for Nvidia P620 on Sept. 7, 2026.