AMD MI455X vs Nvidia P4

The MI455X is newer, with 54x the memory and 121x the bandwidth.

At a glance

Memory

54x more on MI455X

MI455X: 432 GB

P4: 8 GB

Memory bandwidth

121x higher on MI455X

MI455X: 23,300 GB/s

P4: 192 GB/s

Cheapest on-demand

MI455X is not sold on demand

MI455X: --

P4: $0.65 /GPU/hr

Price comparison

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

Billing	MI455X	P4
On-demand	No on-demand listings	-- /GPU/hr from $0.65
Reserved	No reserved listings	-- /GPU/hr from $0.34 (36 mo)
Spot	No spot listings	-- /GPU/hr from $0.12

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: 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

MI455X vs P4 price history

Weekly median on-demand price per GPU per hour

Last 12 months

Aggregating historical prices...

Specs comparison

Spec	MI455X	P4	Difference
Memory
Capacity	432 GB HBM4	8 GB GDDR5	54x more on MI455X
Bandwidth	23,300 GB/s	192 GB/s	121x higher on MI455X
Bus width		256-bit
Compute · dense
FP4	40,265 TFLOPS	Not supported	MI455X only
FP8	20,133 TFLOPS	Not supported	MI455X only
FP16 / BF16	5,033 TFLOPS
INT8	5,033 TOPS	22 TOPS	229x higher on MI455X
FP32	315 TFLOPS	5.5 TFLOPS	57x higher on MI455X
Platform
Interconnect	Infinity Fabric 3,600 GB/s	PCIe only	Infinity Fabric on MI455X only
Released	Q3 2026	Q3 2016	10 years newer on MI455X
Precision
Supported formats	FP4FP6FP8FP16BF16FP32INT8	FP16FP32INT8

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

Source: MI455X datasheet and P4 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	MI455X	P4
Azure USA	On request Custom	--
Cirrascale USA	On request Custom	--
Oracle Cloud USA	On request Custom	--
TensorWave USA	On request Custom	--
Vultr USA	On request Custom	--
Google Cloud USA	--	$0.65 /GPU/hr On-demand