Home
Compare GPUs
Gaudi2 vs GB200

Intel Gaudi2 vs Nvidia GB200

Two data center GPUs, one Gaudi (2nd Gen) and one Grace Blackwell: 96 GB HBM2e against 186 GB HBM3e and 3.3x the memory bandwidth on the GB200.

At a glance

Memory

Gaudi2: 96 GB
GB200: 186 GB

1.9x more on GB200

Memory bandwidth

Gaudi2: 2.45 TB/s
GB200: 8.00 TB/s

3.3x higher on GB200

Cheapest on-demand

Gaudi2: $1.03 /GPU/hr
GB200: $10.50 /GPU/hr

10x more expensive on GB200

Price comparison

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

Billing	Gaudi2	GB200	Difference
On-demand	$1.21 /GPU/hr from $1.03	$16.00 /GPU/hr from $10.50	13x more expensive on GB200
Reserved	-- /GPU/hr from $0.58 (12 mo)	-- /GPU/hr from $10.58
Spot	No spot listings	-- /GPU/hr from $27.04

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 Gaudi2 and reserved and spot on the GB200: 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

Gaudi2 vs GB200 price history

Weekly median on-demand price per GPU per hour

Last 12 months

Aggregating historical prices...

Specs comparison

Spec	Gaudi2	GB200	Difference
Memory
Capacity	96 GB HBM2e	186 GB HBM3e	1.9x more on GB200
Bandwidth	2,450 GB/s	8,000 GB/s	3.3x higher on GB200
Compute · dense
FP4	Not supported	10,000 TFLOPS	GB200 only
FP8	865 TFLOPS	5,000 TFLOPS	5.8x higher on GB200
FP16 / BF16	432 TFLOPS	2,500 TFLOPS	5.8x higher on GB200
INT8		5,000 TOPS
FP32		80 TFLOPS
FP64	Not supported	40 TFLOPS	GB200 only
Platform
Interconnect	RoCE 600 GB/s	NVLink 1,800 GB/s	3x higher on GB200
Board power	600 W	1,200 W	2x higher on GB200
Released	Q2 2022	Q1 2024	2 years newer on GB200
Precision
Supported formats	FP8FP16BF16TF32FP32INT8	FP4FP6FP8FP16BF16TF32FP32FP64INT8

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

Source: Gaudi2 datasheet and GB200 datasheet.

Where to rent them

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

Provider	Gaudi2 /GPU/hr	GB200 /GPU/hr
Runcrate	On-Demand $1.21	--
Sesterce	On-Demand $1.21	--
Cyfuture AI	On-Demand $1.03	--
CoreWeave	--	On-Demand $10.50
Oracle Cloud	--	On-Demand $16.00
Azure	--	On-Demand $27.04
AWS	--	Reservation $10.58
CUDO	--	Custom on request
Canopy Wave	--	Custom on request
Nebius	--	Custom on request
Together AI	--	Custom on request