AMD MI250 vs Nvidia B200

The B200 is newer, with 41% more memory and 2.4x the bandwidth.

At a glance

Memory

41% more on B200

MI250: 128 GB

B200: 180 GB

Memory bandwidth

2.4x higher on B200

MI250: 3.20 TB/s

B200: 7.70 TB/s

Cheapest on-demand

MI250 is not sold on demand

MI250: --

B200: $3.75 /GPU/hr

Price comparison

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

Billing	MI250	B200
On-demand	No on-demand listings	$6.25 /GPU/hr from $3.75
Reserved	-- /GPU/hr from $1.30 (12 mo)	$6.71 /GPU/hr from $3.75
Spot	No spot listings	$4.25 /GPU/hr from $4.18

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 B200 price history

Weekly median on-demand price per GPU per hour

Last 12 months

Aggregating historical prices...

Specs comparison

Spec	MI250	B200	Difference
Memory
Capacity	128 GB HBM2e	180 GB HBM3e	41% more on B200
Bandwidth	3,200 GB/s	7,700 GB/s	2.4x higher on B200
Bus width	8,192-bit
Compute · dense
FP4	Not supported	9,000 TFLOPS	B200 only
FP8	Not supported	4,500 TFLOPS	B200 only
FP16 / BF16	362.1 TFLOPS	2,250 TFLOPS	6.2x higher on B200
INT8	362.1 TOPS	4,500 TOPS	12x higher on B200
FP32	90.5 TFLOPS	75 TFLOPS	21% higher on MI250
FP64	45.3 TFLOPS	37 TFLOPS	22% higher on MI250
Platform
Interconnect	Infinity Fabric 400 GB/s	NVLink 1,800 GB/s	4.5x higher on B200
Board power	500 W	1,000 W	2x higher on B200
Released	Q4 2021	Q1 2024	2 years newer on B200
Precision
Supported formats	FP16BF16FP32FP64INT4INT8	FP4FP6FP8FP16BF16TF32FP32FP64INT8

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

Source: MI250 datasheet and B200 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	B200
Cirrascale USA	$1.30 /GPU/hr Reserved	--
Packet·ai USA	--	$3.75 /GPU/hr On-demand
Lium Distributed	--	$5.64 /GPU/hr On-demand SXM
UpCloud Finland	--	$6.05 /GPU/hr On-demand SXM
GPU.ai UAE	--	$7.99 /GPU/hr On-demand SXM
Runpod USA	--	$7.99 /GPU/hr On-demand SXM
Verda Finland	--	$8.44 /GPU/hr On-demand SXM
Spheron Singapore	--	$11.12 /GPU/hr On-demand SXM
GPUaaS USA	--	$7.00 /GPU/hr Custom