Nvidia P100 vs Nvidia RTX 4000 Ada

The P100 has 2x the bandwidth, while the RTX 4000 Ada is newer and has 25% more memory.

At a glance

Memory

25% more on RTX 4000 Ada

P100: 16 GB

RTX 4000 Ada: 20 GB

Memory bandwidth

2x higher on P100

P100: 732 GB/s

RTX 4000 Ada: 360 GB/s

Cheapest on-demand

52% cheaper on P100

P100: $0.10 /GPU/hr

RTX 4000 Ada: $0.20 /GPU/hr

Price comparison

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

Billing	P100	RTX 4000 Ada	Difference
On-demand	$1.39 /GPU/hr from $0.10	$0.47 /GPU/hr from $0.20	66% cheaper on RTX 4000 Ada
Reserved	$1.04 /GPU/hr from $0.22 (24 mo)	-- /GPU/hr from $0.18 (3 mo)
Spot	-- /GPU/hr from $0.08	-- /GPU/hr from $0.13

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 spot on the P100 and reserved and spot on the RTX 4000 Ada: 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

P100 vs RTX 4000 Ada price history

Weekly median on-demand price per GPU per hour

Last 12 months

Aggregating historical prices...

Specs comparison

Spec	P100	RTX 4000 Ada	Difference
Memory
Capacity	16 GB HBM2	20 GB GDDR6	25% more on RTX 4000 Ada
Bandwidth	732 GB/s	360 GB/s	2x higher on P100
Bus width	4,096-bit	160-bit	26x wider on P100
Compute · dense
FP8	Not supported	213.8 TFLOPS	RTX 4000 Ada only
FP16 / BF16	18.7 TFLOPS	106.9 TFLOPS	5.7x higher on RTX 4000 Ada
FP32	9.3 TFLOPS	26.7 TFLOPS	2.9x higher on RTX 4000 Ada
FP64	4.7 TFLOPS	Not supported	P100 only
Platform
Interconnect	NVLink 160 GB/s	PCIe only	NVLink on P100 only
Board power	250 W	130 W	92% higher on P100
Released	Q2 2016	Q3 2023	7 years newer on RTX 4000 Ada
Precision
Supported formats	FP16FP32FP64	FP8FP16BF16TF32FP32INT4INT8

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: P100 datasheet and RTX 4000 Ada datasheet.

Where to rent them

Providers that rent these GPUs, with each one's cheapest rate. Providers that rent both are listed first.

Provider	P100	RTX 4000 Ada
Vast.ai USA	$0.10 /GPU/hr On-demand	$0.20 /GPU/hr On-demand
Scaleway France	$1.38 /GPU/hr On-demand	--
Oracle Cloud USA	$1.27 /GPU/hr On-demand	--
Google Cloud USA	$1.51 /GPU/hr On-demand	--
Alibaba Cloud China	$1.55 /GPU/hr On-demand	--
Database Mart USA	$0.22 /GPU/hr Reserved	--
Runpod USA	--	$0.20 /GPU/hr On-demand
Akamai Cloud USA	--	$0.52 /GPU/hr On-demand
DigitalOcean USA	--	$0.76 /GPU/hr On-demand
GPU.ai UAE	--	$0.20 /GPU/hr On-demand
Sesterce France	--	$0.87 /GPU/hr On-demand