AMD MI250 vs Nvidia H200

The H200 is newer, with 10% more memory and 50% more bandwidth.

At a glance

Memory

10% more on H200

MI250: 128 GB

H200: 141 GB

Memory bandwidth

50% higher on H200

MI250: 3.20 TB/s

H200: 4.80 TB/s

Cheapest on-demand

MI250 is not sold on demand

MI250: --

H200: $2.09 /GPU/hr

Price comparison

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

Billing	MI250	H200
On-demand	No on-demand listings	$4.81 /GPU/hr from $2.09
Reserved	-- /GPU/hr from $1.30 (12 mo)	$3.84 /GPU/hr from $2.25 (1 mo)
Spot	No spot listings	$3.79 /GPU/hr from $2.61

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: 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 H200 price history

Weekly median on-demand price per GPU per hour

Last 12 months

Aggregating historical prices...

Specs comparison

Spec	MI250	H200	Difference
Memory
Capacity	128 GB HBM2e	141 GB HBM3e	10% more on H200
Bandwidth	3,200 GB/s	4,800 GB/s	50% higher on H200
Bus width	8,192-bit
Compute · dense
FP8	Not supported	1,979 TFLOPS	H200 only
FP16 / BF16	362.1 TFLOPS	989.5 TFLOPS	2.7x higher on H200
INT8	362.1 TOPS	1,979 TOPS	5.5x higher on H200
FP32	90.5 TFLOPS	67 TFLOPS	35% higher on MI250
FP64	45.3 TFLOPS	34 TFLOPS	33% higher on MI250
Platform
Interconnect	Infinity Fabric 400 GB/s	NVLink 900 GB/s	2.2x higher on H200
Board power	500 W	700 W	40% higher on H200
Released	Q4 2021	Q4 2023	2 years newer on H200
Precision
Supported formats	FP16BF16FP32FP64INT4INT8	FP8FP16BF16TF32FP32FP64INT8

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

Source: MI250 datasheet and H200 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	MI250	H200
Cirrascale USA	$1.30 /GPU/hr Reserved	--
Lium Distributed	--	$3.40 /GPU/hr On-demand SXM
Jarvislabs India	--	$3.99 /GPU/hr On-demand SXM
Runcrate USA	--	$4.24 /GPU/hr On-demand SXM
Sesterce France	--	$4.40 /GPU/hr On-demand
Daytona USA	--	$4.54 /GPU/hr On-demand
GPU.ai UAE	--	$5.29 /GPU/hr On-demand SXM
Runpod USA	--	$5.29 /GPU/hr On-demand SXM
Spheron Singapore	--	$5.51 /GPU/hr On-demand SXM