Intel Gaudi 3 vs Nvidia A40

The Gaudi 3 is newer, with 2.7x the memory and 5.3x the bandwidth.

At a glance

Memory

2.7x more on Gaudi 3

Gaudi 3: 128 GB

A40: 48 GB

Memory bandwidth

5.3x higher on Gaudi 3

Gaudi 3: 3,700 GB/s

A40: 696 GB/s

Cheapest on-demand

Gaudi 3 is not sold on demand

Gaudi 3: --

A40: $0.59 /GPU/hr

Price comparison

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

Billing	Gaudi 3	A40	Difference
On-demand	No on-demand listings	$0.85 /GPU/hr from $0.59
Reserved	No reserved listings	-- /GPU/hr from $0.61 (24 mo)

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 A40: 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

Gaudi 3 vs A40 price history

Weekly median on-demand price per GPU per hour

Last 12 months

Aggregating historical prices...

Specs comparison

Spec	Gaudi 3	A40	Difference
Memory
Capacity	128 GB HBM2e	48 GB GDDR6	2.7x more on Gaudi 3
Bandwidth	3,700 GB/s	696 GB/s	5.3x higher on Gaudi 3
Bus width		384-bit
Compute · dense
FP8	1,678 TFLOPS	Not supported	Gaudi 3 only
FP16 / BF16	1,678 TFLOPS	149.7 TFLOPS	11x higher on Gaudi 3
INT8	Not supported	299.3 TOPS	A40 only
FP32		37.4 TFLOPS
Platform
Interconnect	RoCE 1,200 GB/s	PCIe only	RoCE on Gaudi 3 only
Board power	900 W	300 W	3x higher on Gaudi 3
Released	Q2 2024	Q4 2020	4 years newer on Gaudi 3
Precision
Supported formats	FP8FP16BF16TF32FP32	FP16BF16TF32FP32INT4INT8

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

Source: Gaudi 3 datasheet and A40 datasheet.

Where to rent them

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

Provider	Gaudi 3	A40
Denvr Canada	On request Custom	$0.65 /GPU/hr On-demand
GPU.ai UAE	--	$0.59 /GPU/hr On-demand
Runpod USA	--	$0.59 /GPU/hr On-demand
Sesterce France	--	$2.05 /GPU/hr On-demand
Runcrate USA	--	$2.42 /GPU/hr On-demand PCIe
Exoscale Switzerland	--	$1.05 /GPU/hr On-demand
Database Mart USA	--	$0.61 /GPU/hr Reserved
EmpirioLabs AI USA	--	$1.49 /GPU/hr On-demand