Nvidia K620 vs Nvidia RTX 4090

The RTX 4090 is newer, with 12x the memory and 35x the bandwidth.

At a glance

Memory

12x more on RTX 4090

K620: 2 GB

RTX 4090: 24 GB

Memory bandwidth

35x higher on RTX 4090

K620: 29 GB/s

RTX 4090: 1,010 GB/s

Cheapest on-demand

K620: --

RTX 4090: $0.33 /GPU/hr

Price comparison

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

Billing	K620	RTX 4090
On-demand	No on-demand listings	$0.48 /GPU/hr from $0.33
Reserved	No reserved listings	$0.52 /GPU/hr from $0.29 (1 mo)
Spot	No spot listings	$0.33 /GPU/hr from $0.16

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

K620 vs RTX 4090 price history

Weekly median on-demand price per GPU per hour

Last 17 months

Aggregating historical prices...

Specs comparison

Spec	K620	RTX 4090	Difference
Memory
Capacity	2 GB DDR3	24 GB GDDR6X	12x more on RTX 4090
Bandwidth	29 GB/s	1,010 GB/s	35x higher on RTX 4090
Bus width	128-bit	384-bit	3x wider on RTX 4090
Compute · dense
FP8	Not supported	330.3 TFLOPS	RTX 4090 only
FP16 / BF16	Not supported	165.2 TFLOPS	RTX 4090 only
INT8	Not supported	660.6 TOPS	RTX 4090 only
FP32	0.9 TFLOPS	82.6 TFLOPS	96x higher on RTX 4090
Platform
Interconnect	PCIe only	PCIe only
Board power	45 W	450 W	10x higher on RTX 4090
Released	Q3 2014	Q4 2022	8 years newer on RTX 4090
Precision
Supported formats	FP32	FP8FP16BF16TF32FP32INT4INT8

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

Source: K620 datasheet and RTX 4090 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	K620	RTX 4090
Vast.ai USA	--	$0.34 /GPU/hr On-demand
GPU.ai UAE	--	$0.34 /GPU/hr On-demand
Runpod USA	--	$0.34 /GPU/hr On-demand
Packet·ai USA	--	$0.39 /GPU/hr On-demand
GPUhub Singapore	--	$0.44 /GPU/hr On-demand
Lium Distributed	--	$0.58 /GPU/hr On-demand
Oblivus USA	--	$0.64 /GPU/hr On-demand PCIe
Sesterce France	--	$0.66 /GPU/hr On-demand