AMD MI325X vs AMD MI350P

The MI325X has 78% more memory and 50% more bandwidth.

At a glance

Memory

78% more on MI325X

MI325X: 256 GB

MI350P: 144 GB

Memory bandwidth

50% higher on MI325X

MI325X: 6.00 TB/s

MI350P: 4.00 TB/s

Cheapest on-demand

MI325X: $2.45 /GPU/hr

MI350P: --

Price comparison

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

Billing	MI325X	MI350P
On-demand	$3.11 /GPU/hr from $2.45	No on-demand listings
Reserved	$2.20 /GPU/hr from $1.50 (12 mo)	No reserved listings
Spot	Sold out	No spot listings

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

MI325X vs MI350P price history

Weekly median on-demand price per GPU per hour

Last 12 months

Aggregating historical prices...

Specs comparison

Spec	MI325X	MI350P	Difference
Memory
Capacity	256 GB HBM3e	144 GB HBM3e	78% more on MI325X
Bandwidth	6,000 GB/s	4,000 GB/s	50% higher on MI325X
Bus width	8,192-bit	4,096-bit	2x wider on MI325X
Compute · dense
FP4	Not supported	4,600 TFLOPS	MI350P only
FP8	2,614.9 TFLOPS	2,300 TFLOPS	14% higher on MI325X
FP16 / BF16	1,307.4 TFLOPS	1,150 TFLOPS	14% higher on MI325X
INT8	2,614.9 TOPS	2,300 TOPS	14% higher on MI325X
FP32	163.4 TFLOPS	72 TFLOPS	2.3x higher on MI325X
FP64	81.7 TFLOPS	36 TFLOPS	2.3x higher on MI325X
Platform
Interconnect	Infinity Fabric 896 GB/s	PCIe only	Infinity Fabric on MI325X only
Board power	1,000 W	600 W	67% higher on MI325X
Released	Q4 2024	Q2 2026	2 years newer on MI350P
Precision
Supported formats	FP8FP16BF16TF32FP32FP64INT8	FP4FP6FP8FP16BF16FP32FP64INT8

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

Source: MI325X datasheet and MI350P 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	MI325X	MI350P
Bentaus USA	$2.45 /GPU/hr On-demand	--
Cyfuture AI India	$3.06 /GPU/hr On-demand	--
DigitalOcean USA	$3.80 /GPU/hr On-demand	--
TensorWave USA	$2.25 /GPU/hr Custom OAM	--
OpenRelay USA	$2.25 /GPU/hr On-demand	--
Vultr USA	$2.00 /GPU/hr Spot	--