AMD MI250 vs AMD MI350X

Two AMD data center GPUs, one CDNA2 and one CDNA 4: 128 GB HBM2e against 288 GB HBM3e and 2.5x the memory bandwidth on the MI350X.

At a glance

Memory

MI250: 128 GB
MI350X: 288 GB

2.2x more on MI350X

Memory bandwidth

MI250: 3.20 TB/s
MI350X: 8.00 TB/s

2.5x higher on MI350X

Cheapest on-demand

MI250: --
MI350X: --

MI250 and MI350X are not sold on demand

Price comparison

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

Billing	MI250	MI350X	Difference
Reserved	-- /GPU/hr from $1.30 (12 mo)	-- /GPU/hr from $4.76 (12 mo)
Spot	No spot listings	-- /GPU/hr from $4.00

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 reserved on the MI250 and reserved and spot on the MI350X: 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

MI250 vs MI350X price history

Weekly median on-demand price per GPU per hour

Last 12 months

Aggregating historical prices...

Specs comparison

Spec	MI250	MI350X	Difference
Memory
Capacity	128 GB HBM2e	288 GB HBM3e	2.2x more on MI350X
Bandwidth	3,200 GB/s	8,000 GB/s	2.5x higher on MI350X
Bus width	8,192-bit	8,192-bit	Identical
Compute · dense
FP4	Not supported	9,227.5 TFLOPS	MI350X only
FP8	Not supported	4,614 TFLOPS	MI350X only
FP16 / BF16	362.1 TFLOPS	2,309.6 TFLOPS	6.4x higher on MI350X
INT8	362.1 TOPS	4,614 TOPS	13x higher on MI350X
FP32	90.5 TFLOPS	144.2 TFLOPS	1.6x higher on MI350X
FP64	45.3 TFLOPS	72.1 TFLOPS	1.6x higher on MI350X
Platform
Interconnect	Infinity Fabric 400 GB/s	Infinity Fabric 1,075 GB/s	2.7x higher on MI350X
Board power	500 W	1,000 W	2x higher on MI350X
Released	Q4 2021	Q2 2025	4 years newer on MI350X
Precision
Supported formats	FP16BF16FP32FP64INT4INT8	FP4FP6FP8FP16BF16FP32FP64INT8