AMD MI300X vs AMD MI355X

The MI355X is newer, with 50% more memory and 51% more bandwidth. The MI300X is cheaper right now.

At a glance

Memory

50% more on MI355X

MI300X: 192 GB

MI355X: 288 GB

Memory bandwidth

51% higher on MI355X

MI300X: 5.30 TB/s

MI355X: 8.00 TB/s

Cheapest on-demand

57% cheaper on MI300X

MI300X: $2.59 /GPU/hr

MI355X: $5.99 /GPU/hr

Price comparison

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

Billing	MI300X	MI355X
On-demand	$4.41 /GPU/hr from $2.59	-- /GPU/hr from $5.99
Reserved	$3.39 /GPU/hr from $1.61 (12 mo)	No reserved listings
Spot	-- /GPU/hr from $1.60	-- /GPU/hr from $2.97

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 spot on the MI300X and on-demand and spot on the MI355X: 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

MI300X vs MI355X price history

Weekly median on-demand price per GPU per hour

Last 12 months

Aggregating historical prices...

Specs comparison

Spec	MI300X	MI355X	Difference
Memory
Capacity	192 GB HBM3	288 GB HBM3e	50% more on MI355X
Bandwidth	5,300 GB/s	8,000 GB/s	51% higher on MI355X
Bus width	8,192-bit	8,192-bit	Identical
Compute · dense
FP4	Not supported	10,066.3 TFLOPS	MI355X only
FP8	2,614.9 TFLOPS	5,033.2 TFLOPS	92% higher on MI355X
FP16 / BF16	1,307.4 TFLOPS	2,516.6 TFLOPS	92% higher on MI355X
INT8	2,614.9 TOPS	5,033.2 TOPS	92% higher on MI355X
FP32	163.4 TFLOPS	157.3 TFLOPS	Within 5%
FP64	81.7 TFLOPS	78.6 TFLOPS	Within 5%
Platform
Interconnect	Infinity Fabric 896 GB/s	Infinity Fabric 1,075 GB/s	20% higher on MI355X
Board power	750 W	1,400 W	87% higher on MI355X
Released	Q4 2023	Q2 2025	2 years newer on MI355X
Precision
Supported formats	FP8FP16BF16TF32FP32FP64INT8	FP4FP6FP8FP16BF16FP32FP64INT8

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

Source: MI300X datasheet and MI355X datasheet.

Where to rent them

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

Provider	MI300X	MI355X
Oracle Cloud USA	$6.00 /GPU/hr On-demand	$8.60 /GPU/hr On-demand
DigitalOcean USA	$2.59 /GPU/hr On-demand	$2.97 /GPU/hr Spot
Crusoe USA	On request Reserved	On request Custom
Hot Aisle USA	$3.39 /GPU/hr Reserved	--
Denvr Canada	On request Custom	--
Cyfuture AI India	$2.76 /GPU/hr On-demand	--
Azure USA	$7.86 /GPU/hr On-demand	--
Cirrascale USA	$3.12 /GPU/hr Reserved	--
Daytona USA	--	$5.99 /GPU/hr On-demand
TensorWave USA	--	$2.95 /GPU/hr Custom OAM
Vultr USA	--	$2.59 /GPU/hr Spot