Nvidia P40 vs Nvidia RTX 4000

The RTX 4000 is newer and has 20% more bandwidth, while the P40 has 3x the memory. The P40 is cheaper right now.

At a glance

Memory

3x more on P40

P40: 24 GB

RTX 4000: 8 GB

Memory bandwidth

20% higher on RTX 4000

P40: 346 GB/s

RTX 4000: 416 GB/s

Cheapest on-demand

85% cheaper on P40

P40: $0.08 /GPU/hr

RTX 4000: $0.56 /GPU/hr

Price comparison

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

Billing	P40	RTX 4000	Difference
On-demand	-- /GPU/hr from $0.08	-- /GPU/hr from $0.56
Spot	-- /GPU/hr from $0.07	No spot 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. No median for on-demand and spot on the P40 and on-demand on the RTX 4000: 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

P40 vs RTX 4000 price history

Weekly median on-demand price per GPU per hour

Last 13 months

Aggregating historical prices...

Specs comparison

Spec	P40	RTX 4000	Difference
Memory
Capacity	24 GB GDDR5	8 GB GDDR6	3x more on P40
Bandwidth	346 GB/s	416 GB/s	20% higher on RTX 4000
Bus width	384-bit	256-bit	50% wider on P40
Compute · dense
FP16 / BF16		57 TFLOPS
INT8	47 TOPS
FP32	12 TFLOPS	7.1 TFLOPS	69% higher on P40
Platform
Interconnect	PCIe only	PCIe only
Board power	250 W	160 W	56% higher on P40
Released	Q3 2016	Q4 2018	2 years newer on RTX 4000
Precision
Supported formats	FP16FP32INT8	FP16FP32INT4INT8