Home
Compare GPUs
A30 vs B100

Nvidia A30 vs Nvidia B100

Two Nvidia data center GPUs, one Ampere and one Blackwell: 24 GB HBM2 against up to 192 GB HBM3e, 8.6x the memory bandwidth on the B100, and NVLink 1,800 GB/s on the B100 where the A30 is PCIe only.

At a glance

Updated 8 minutes ago

Nvidia A30

Memory: 24 GB; HBM2
Memory bandwidth: 933 GB/s
From: $0.70 /GPU/hr; 7 providers

Nvidia B100

Memory: 192 GB; HBM3e
Memory bandwidth: 8.00 TB/s
From: --

Price comparison

Cheapest listed price per GPU per hour by billing type, and the median across providers.

Billing	A30	B100
On-demand	$0.70	--
Reserved	$0.43	No reserved listings
Median	$0.77	--

Median: Median across providers, one vote each, so a large catalog does not outweigh a small one.

Price history

A30 vs B100 price history

Weekly median on-demand price per GPU per hour

Last 12 months

Aggregating historical prices...

Specs comparison

Spec	A30	B100	Difference
Memory
Capacity	24 GB HBM2	192 GB HBM3e	8x more on B100
Bandwidth	933 GB/s	8,000 GB/s	8.6x higher on B100
Compute · dense
FP4	Not supported	7,000 TFLOPS	B100 only
FP8	Not supported	3,500 TFLOPS	B100 only
FP16 / BF16	165 TFLOPS	1,750 TFLOPS	11x higher on B100
INT8	330 TOPS	3,500 TOPS	11x higher on B100
FP32	10.3 TFLOPS	60 TFLOPS	5.8x higher on B100
FP64	5.2 TFLOPS	30 TFLOPS	5.8x higher on B100
Platform
Interconnect	PCIe only	NVLink 1,800 GB/s	NVLink on B100 only
Released	Q2 2021	Q4 2024	4 years newer on B100
Precision
Supported formats	FP16BF16TF32FP32FP64INT4INT8	FP4FP6FP8FP16BF16TF32FP32FP64INT8

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

Source: A30 datasheet and B100 datasheet.

Where to rent them

Providers listing these GPUs, those with both first, so you can switch without moving clouds.

Provider	A30 /GPU/hr	B100 /GPU/hr
Leafcloud	On-Demand $0.70	--
Exoscale	On-Demand $0.74	--
Leaseweb	Reserved (1mo) $0.43	--
AceCloud	Reserved (12mo) $0.67	--
Massed Compute	On-Demand $0.35	--
Sesterce	On-Demand $0.39	--
EmpirioLabs AI	On-Demand $0.55	--