AMD MI455X vs Nvidia T4

The MI455X is newer, with 27x the memory and 78x the bandwidth.

At a glance

Memory

27x more on MI455X

MI455X: 432 GB

T4: 16 GB

Memory bandwidth

78x higher on MI455X

MI455X: 23,300 GB/s

T4: 300 GB/s

Cheapest on-demand

MI455X is not sold on demand

MI455X: --

T4: $0.11 /GPU/hr

Price comparison

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

Billing	MI455X	T4
On-demand	No on-demand listings	$0.64 /GPU/hr from $0.11
Reserved	No reserved listings	$0.43 /GPU/hr from $0.20 (36 mo)
Spot	No spot listings	$0.26 /GPU/hr from $0.06

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. Verify before provisioning. More on how we price.

Price history

MI455X vs T4 price history

Weekly median on-demand price per GPU per hour

Last 12 months

Aggregating historical prices...

Specs comparison

Spec	MI455X	T4	Difference
Memory
Capacity	432 GB HBM4	16 GB GDDR6	27x more on MI455X
Bandwidth	23,300 GB/s	300 GB/s	78x 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	65 TFLOPS	77x higher on MI455X
INT8	5,033 TOPS	130 TOPS	39x higher on MI455X
FP32	315 TFLOPS	8.1 TFLOPS	39x higher on MI455X
Platform
Interconnect	Infinity Fabric 3,600 GB/s	PCIe only	Infinity Fabric on MI455X only
Released	Q3 2026	Q3 2018	8 years newer on MI455X
Precision
Supported formats	FP4FP6FP8FP16BF16FP32INT8	FP16FP32INT4INT8

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

Source: MI455X datasheet and T4 datasheet.

Where to rent them

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

Provider	MI455X	T4
Azure USA	On request Custom	$0.53 /GPU/hr On-demand
Cirrascale USA	On request Custom	--
Oracle Cloud USA	On request Custom	--
TensorWave USA	On request Custom	--
Vultr USA	On request Custom	--
Vast.ai USA	--	$0.11 /GPU/hr On-demand
Zenlayer USA	--	$0.56 /GPU/hr On-demand PCIe
Theta EdgeCloud Distributed	--	$0.20 /GPU/hr On-demand
Hugging Face USA	--	$0.40 /GPU/hr On-demand
Google Cloud USA	--	$0.42 /GPU/hr On-demand
AWS USA	--	$0.53 /GPU/hr On-demand
Cerebrium USA	--	$0.59 /GPU/hr On-demand