AMD MI210 vs Nvidia A100

The A100 has 25% more memory and 18% more bandwidth.

At a glance

Memory

25% more on A100

MI210: 64 GB

A100: 80 GB

Memory bandwidth

18% higher on A100

MI210: 1.64 TB/s

A100: 1.94 TB/s

Cheapest on-demand

MI210 is not sold on demand

MI210: --

A100: $0.89 /GPU/hr

Price comparison

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

Billing	MI210	A100
On-demand	No on-demand listings	$1.88 /GPU/hr from $0.89
Reserved	-- /GPU/hr from $0.85 (1 mo)	$1.67 /GPU/hr from $0.66 (24 mo)
Spot	No spot listings	$1.19 /GPU/hr from $0.68

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 MI210: 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

MI210 vs A100 price history

Weekly median on-demand price per GPU per hour

Last 12 months

Aggregating historical prices...

Specs comparison

Spec	MI210	A100	Difference
Memory
Capacity	64 GB HBM2e	80 GB HBM2e 40 GB on SXM, PCIe	25% more on A100
Bandwidth	1,638 GB/s	1,935 GB/s 2,039 GB/s on SXM 1,555 GB/s on SXM, PCIe	18% higher on A100
Bus width	4,096-bit	5,120-bit	25% wider on A100
Compute · dense
FP16 / BF16	181 TFLOPS	312 TFLOPS	72% higher on A100
INT8	181 TOPS	624 TOPS	3.4x higher on A100
FP32	45.3 TFLOPS	19.5 TFLOPS	2.3x higher on MI210
FP64	22.6 TFLOPS	9.7 TFLOPS	2.3x higher on MI210
Platform
Interconnect	Infinity Fabric 300 GB/s	NVLink 600 GB/s	2x higher on A100
Board power	300 W	300 W	Identical
Released	Q1 2022	Q2 2020	2 years newer on MI210
Precision
Supported formats	FP16BF16FP32FP64INT4INT8	FP16BF16TF32FP32FP64INT4INT8

Figures are for each model's headline configuration. Where a form factor carries a different number, it is named under the figure.

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

Source: MI210 datasheet and A100 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	MI210	A100
Leaseweb Netherlands	$0.85 /GPU/hr Reserved	--
Jarvislabs India	--	$0.89 /GPU/hr On-demand
Runpod USA	--	$1.00 /GPU/hr On-demand SXM
GPU.ai UAE	--	$1.07 /GPU/hr On-demand
Thunder Compute USA	--	$1.09 /GPU/hr On-demand
Hyperstack UK	--	$1.35 /GPU/hr On-demand PCIe
Massed Compute USA	--	$1.35 /GPU/hr On-demand
Spheron Singapore	--	$1.43 /GPU/hr On-demand PCIe
Oblivus USA	--	$1.47 /GPU/hr On-demand PCIe