AMD MI355X vs Nvidia P100

Two data center GPUs, one CDNA 4 and one Pascal: 288 GB HBM3e against 16 GB HBM2 and 11x the memory bandwidth on the MI355X.

At a glance

Updated 3 minutes ago

AMD MI355X

Nvidia P100

Cheapest listed price per GPU per hour by billing type, and the median across providers.

Billing	MI355X	P100	Difference
On-demand	$8.60	$0.09	91x more expensive on MI355X
Spot	$4.50	$0.08	56x more expensive on MI355X
Reserved	No reserved listings	$0.12
Median	$8.60	$1.42	6.1x more expensive on MI355X

Median: Median across providers, one vote each, so a large catalog does not outweigh a small one.

Weekly median on-demand price per GPU per hour

Last 12 months

Aggregating historical prices...

Spec	MI355X	P100	Difference
Memory
Capacity	288 GB HBM3e	16 GB HBM2	18x more on MI355X
Bandwidth	8,000 GB/s	732 GB/s	11x higher on MI355X
Bus width	8,192-bit	4,096-bit	2x wider on MI355X
Compute · dense
FP4	10,066.3 TFLOPS	Not supported	MI355X only
FP8	5,033.2 TFLOPS	Not supported	MI355X only
FP16 / BF16	2,516.6 TFLOPS	18.7 TFLOPS	135x higher on MI355X
INT8	5,033.2 TOPS	Not supported	MI355X only
FP32	157.3 TFLOPS	9.3 TFLOPS	17x higher on MI355X
FP64	78.6 TFLOPS	4.7 TFLOPS	17x higher on MI355X
Platform
Interconnect	Infinity Fabric 1,075 GB/s	NVLink 160 GB/s	6.7x higher on MI355X
Board power	1,400 W	250 W	5.6x higher on MI355X
Released	Q2 2025	Q2 2016	9 years newer on MI355X
Precision
Supported formats	FP4FP6FP8FP16BF16FP32FP64INT8	FP16FP32FP64

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.

Providers listing these GPUs, those with both first, so you can switch without moving clouds.