AMD MI355X vs Nvidia GH200

Two data center GPUs, one CDNA 4 and one Grace Hopper: 288 GB HBM3e against 96 GB HBM3 and 2x the memory bandwidth on the MI355X.

At a glance

Updated 6 minutes ago

AMD MI355X

Nvidia GH200

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

Billing	MI355X	GH200	Difference
On-demand	$8.60	$2.52	3.4x more expensive on MI355X
Spot	$4.50	No spot listings
Median	$8.60	$4.51	48% cheaper on GH200

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	GH200	Difference
Memory
Capacity	288 GB HBM3e	96 GB HBM3	3x more on MI355X
Bandwidth	8,000 GB/s	4,000 GB/s	2x higher on MI355X
Bus width	8,192-bit
Compute · dense
FP4	10,066.3 TFLOPS	Not supported	MI355X only
FP8	5,033.2 TFLOPS	1,979 TFLOPS	2.5x higher on MI355X
FP16 / BF16	2,516.6 TFLOPS	989.5 TFLOPS	2.5x higher on MI355X
INT8	5,033.2 TOPS	1,979 TOPS	2.5x higher on MI355X
FP32	157.3 TFLOPS	67 TFLOPS	2.3x higher on MI355X
FP64	78.6 TFLOPS	34 TFLOPS	2.3x higher on MI355X
Platform
Interconnect	Infinity Fabric 1,075 GB/s	NVLink 900 GB/s	1.2x higher on MI355X
Released	Q2 2025	Q2 2023	2 years newer on MI355X
Precision
Supported formats	FP4FP6FP8FP16BF16FP32FP64INT8	FP8FP16BF16TF32FP32FP64INT8

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.