Nvidia A30 vs Nvidia H100

The H100 is newer, with 3.3x the memory and 3.6x the bandwidth. The A30 is typically cheaper.

At a glance

Memory

3.3x more on H100

A30: 24 GB

H100: 80 GB

Memory bandwidth

3.6x higher on H100

A30: 933 GB/s

H100: 3,350 GB/s

Cheapest on-demand

68% cheaper on A30

A30: $0.41 /GPU/hr

H100: $1.30 /GPU/hr

Price comparison

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

Billing	A30	H100	Difference
On-demand	$0.69 /GPU/hr from $0.41	$3.38 /GPU/hr from $1.30	80% cheaper on A30
Reserved	$0.58 /GPU/hr from $0.38 (12 mo)	$3.12 /GPU/hr from $1.53 (1 mo)	81% cheaper on A30
Spot	-- /GPU/hr from $0.29	$2.00 /GPU/hr from $0.36

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 spot on the A30: 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

A30 vs H100 price history

Weekly median on-demand price per GPU per hour

Last 12 months

Aggregating historical prices...

Specs comparison

Spec	A30	H100	Difference
Memory
Capacity	24 GB HBM2	80 GB HBM3 94 GB on NVL	3.3x more on H100
Bandwidth	933 GB/s	3,350 GB/s 2,000 GB/s on PCIe 3,938 GB/s on NVL	3.6x higher on H100
Bus width		5,120-bit
Compute · dense
FP8	Not supported	1,979 TFLOPS	H100 only
FP16 / BF16	165 TFLOPS	989.5 TFLOPS	6x higher on H100
INT8	330 TOPS	1,979 TOPS	6x higher on H100
FP32	10.3 TFLOPS	67 TFLOPS	6.5x higher on H100
FP64	5.2 TFLOPS	34 TFLOPS	6.5x higher on H100
Platform
Interconnect	PCIe only	NVLink 900 GB/s NVLink 600 GB/s on PCIe, NVL	NVLink on H100 only
Board power	165 W	700 W	4.2x higher on H100
Released	Q2 2021	Q3 2022	17 months newer on H100
Precision
Supported formats	FP16BF16TF32FP32FP64INT4INT8	FP8FP16BF16TF32FP32FP64INT8

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: A30 datasheet and H100 datasheet.

Where to rent them

Providers that rent these GPUs, with each one's cheapest rate. Providers that rent both are listed first.

Provider	A30	H100
Jarvislabs India	$0.41 /GPU/hr On-demand	$2.69 /GPU/hr On-demand SXM
EmpirioLabs AI USA	$0.55 /GPU/hr On-demand	$2.60 /GPU/hr On-demand
Leafcloud Netherlands	$0.68 /GPU/hr On-demand PCIe	--
Exoscale Switzerland	$0.74 /GPU/hr On-demand	--
Leaseweb Netherlands	$0.45 /GPU/hr Reserved	--
AceCloud India	$0.67 /GPU/hr Reserved	--
Massed Compute USA	$0.35 /GPU/hr On-demand	--
Sesterce France	$0.39 /GPU/hr On-demand	--
Lium Distributed	--	$1.30 /GPU/hr On-demand SXM
Vast.ai USA	--	$1.73 /GPU/hr On-demand SXM
HyperAI Hong Kong	--	$1.80 /GPU/hr On-demand
GPU.ai UAE	--	$2.48 /GPU/hr On-demand PCIe
Hyperstack UK	--	$2.50 /GPU/hr On-demand PCIe
Runpod USA	--	$2.59 /GPU/hr On-demand NVL