Home
Compare GPUs
P4 vs T4G

Nvidia P4 vs Nvidia T4G

Two Nvidia data center GPUs, one Pascal and one Turing: 8 GB GDDR5 against 16 GB GDDR6 and 67% more memory bandwidth on the T4G.

At a glance

Memory

P4: 8 GB
T4G: 16 GB

2x more on T4G

Memory bandwidth

P4: 192 GB/s
T4G: 320 GB/s

1.7x higher on T4G

Cheapest on-demand

P4: $0.65 /GPU/hr
T4G: $0.42 /GPU/hr

36% cheaper on T4G

Price comparison

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

Billing	P4	T4G
On-demand	-- /GPU/hr from $0.65	-- /GPU/hr from $0.42
Reserved	-- /GPU/hr from $0.34 (36 mo)	-- /GPU/hr from $0.18 (36 mo)
Spot	-- /GPU/hr from $0.12	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, reserved and spot on the P4 and on-demand and reserved on the T4G: 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

P4 vs T4G price history

Weekly median on-demand price per GPU per hour

Last 12 months

Aggregating historical prices...

Specs comparison

Spec	P4	T4G	Difference
Memory
Capacity	8 GB GDDR5	16 GB GDDR6	2x more on T4G
Bandwidth	192 GB/s	320 GB/s	1.7x higher on T4G
Bus width	256-bit	256-bit	Identical
Compute · dense
FP16 / BF16		65 TFLOPS
INT8	22 TOPS	130 TOPS	5.9x higher on T4G
FP32	5.5 TFLOPS	8.1 TFLOPS	1.5x higher on T4G
Platform
Interconnect	PCIe only	PCIe only
Board power	75 W	70 W	1.1x higher on P4
Released	Q3 2016	Q3 2020	4 years newer on T4G
Precision
Supported formats	FP16FP32INT8	FP16FP32INT4INT8