AMD MI350P vs Nvidia A100

The MI350P is newer, with 80% more memory and 2.1x the bandwidth.

At a glance

Memory

80% more on MI350P

MI350P: 144 GB

A100: 80 GB

Memory bandwidth

2.1x higher on MI350P

MI350P: 4.00 TB/s

A100: 1.94 TB/s

Cheapest on-demand

MI350P: --

A100: $0.81 /GPU/hr

Price comparison

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

Billing	MI350P	A100
On-demand	No on-demand listings	$2.00 /GPU/hr from $0.81
Reserved	No reserved listings	$1.60 /GPU/hr from $0.66 (24 mo)
Spot	No spot listings	$1.05 /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. Verify before provisioning. More on how we price.

Price history

MI350P vs A100 price history

Weekly median on-demand price per GPU per hour

Last 12 months

Aggregating historical prices...

Specs comparison

Spec	MI350P	A100	Difference
Memory
Capacity	144 GB HBM3e	80 GB HBM2e 40 GB on SXM, PCIe	80% more on MI350P
Bandwidth	4,000 GB/s	1,935 GB/s 2,039 GB/s on SXM 1,555 GB/s on SXM, PCIe	2.1x higher on MI350P
Bus width	4,096-bit	5,120-bit	25% wider on A100
Compute · dense
FP4	4,600 TFLOPS	Not supported	MI350P only
FP8	2,300 TFLOPS	Not supported	MI350P only
FP16 / BF16	1,150 TFLOPS	312 TFLOPS	3.7x higher on MI350P
INT8	2,300 TOPS	624 TOPS	3.7x higher on MI350P
FP32	72 TFLOPS	19.5 TFLOPS	3.7x higher on MI350P
FP64	36 TFLOPS	9.7 TFLOPS	3.7x higher on MI350P
Platform
Interconnect	PCIe only	NVLink 600 GB/s	NVLink on A100 only
Board power	600 W	300 W	2x higher on MI350P
Released	Q2 2026	Q2 2020	6 years newer on MI350P
Precision
Supported formats	FP4FP6FP8FP16BF16FP32FP64INT8	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: MI350P 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	MI350P	A100
Lium Distributed	--	$0.81 /GPU/hr On-demand PCIe
Jarvislabs India	--	$0.89 /GPU/hr On-demand
Thunder Compute USA	--	$1.09 /GPU/hr On-demand
OpenRelay USA	--	$1.10 /GPU/hr On-demand
Massed Compute USA	--	$1.35 /GPU/hr On-demand
Runpod USA	--	$1.39 /GPU/hr On-demand SXM
GPU.ai UAE	--	$1.41 /GPU/hr On-demand
Sesterce France	--	$1.49 /GPU/hr On-demand