Nvidia M4000 vs Nvidia RTX 3080

A workstation GPU against a consumer card, one Maxwell and one Ampere: 8 GB GDDR5 against 10 GB GDDR6X and 4x the memory bandwidth on the RTX 3080.

At a glance

Updated 5 minutes ago

Nvidia M4000

Nvidia RTX 3080

Cheapest listed price per GPU per hour by billing type, and the median across providers.

Billing	M4000	RTX 3080	Difference
On-demand	$0.45	$0.10	4.7x more expensive on M4000
Spot	No spot listings	$0.06
Reserved	No reserved listings	$0.12
Median	$0.45	$0.16	2.9x more expensive on M4000

Median: Median across providers, one vote each, so a large catalog does not outweigh a small one.

Weekly median on-demand price per GPU per hour

Last 12 months

Aggregating historical prices...

Spec	M4000	RTX 3080	Difference
Memory
Capacity	8 GB GDDR5	10 GB GDDR6X	1.2x more on RTX 3080
Bandwidth	192 GB/s	760 GB/s	4x higher on RTX 3080
Bus width	256-bit	320-bit	1.2x wider on RTX 3080
Compute · dense
FP16 / BF16	Not supported	59.5 TFLOPS	RTX 3080 only
INT8	Not supported	238 TOPS	RTX 3080 only
FP32	2.6 TFLOPS	29.8 TFLOPS	12x higher on RTX 3080
Platform
Interconnect	PCIe only	PCIe only
Board power	120 W	320 W	2.7x higher on RTX 3080
Released	Q2 2015	Q3 2020	5 years newer on RTX 3080
Precision
Supported formats	FP32	FP16BF16TF32FP32INT4INT8

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.

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