AMD MI325X vs Nvidia Vera Rubin

The Vera Rubin is newer, with 13% more memory and 3.2x the bandwidth.

At a glance

Memory

13% more on Vera Rubin

MI325X: 256 GB

Vera Rubin: 288 GB

Memory bandwidth

3.2x higher on Vera Rubin

MI325X: 6.00 TB/s

Vera Rubin: 19.20 TB/s

Cheapest on-demand

Vera Rubin is not sold on demand

MI325X: $2.45 /GPU/hr

Vera Rubin: --

Price comparison

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

Billing	MI325X	Vera Rubin
On-demand	$3.12 /GPU/hr from $2.45	No on-demand listings
Reserved	$2.20 /GPU/hr from $1.51 (12 mo)	-- /GPU/hr
Spot	Sold out	No spot listings

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 Vera Rubin: 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

MI325X vs Vera Rubin price history

Weekly median on-demand price per GPU per hour

Last 12 months

Aggregating historical prices...

Specs comparison

Spec	MI325X	Vera Rubin	Difference
Memory
Capacity	256 GB HBM3e	288 GB HBM4	13% more on Vera Rubin
Bandwidth	6,000 GB/s	19,200 GB/s	3.2x higher on Vera Rubin
Bus width	8,192-bit
Compute · dense
FP4	Not supported	35,000 TFLOPS	Vera Rubin only
FP8	2,614.9 TFLOPS	17,500 TFLOPS	6.7x higher on Vera Rubin
FP16 / BF16	1,307.4 TFLOPS	4,000 TFLOPS	3.1x higher on Vera Rubin
INT8	2,614.9 TOPS	250 TOPS	10x higher on MI325X
FP32	163.4 TFLOPS	130 TFLOPS	26% higher on MI325X
FP64	81.7 TFLOPS	33 TFLOPS	2.5x higher on MI325X
Platform
Interconnect	Infinity Fabric 896 GB/s	NVLink 3,000 GB/s	3.3x higher on Vera Rubin
Released	Q4 2024	Q1 2026	15 months newer on Vera Rubin
Precision
Supported formats	FP8FP16BF16TF32FP32FP64INT8	FP4FP6FP8FP16BF16TF32FP32FP64INT8

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

Source: MI325X datasheet and Vera Rubin 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	MI325X	Vera Rubin
Bentaus USA	$2.45 /GPU/hr On-demand	--
Cyfuture AI India	$3.08 /GPU/hr On-demand	--
DigitalOcean USA	$3.80 /GPU/hr On-demand	--
TensorWave USA	$2.25 /GPU/hr Custom OAM	--
OpenRelay USA	$2.25 /GPU/hr On-demand	--
Vultr USA	$2.00 /GPU/hr Spot	--
Impossible Cloud Germany	--	$11.05 /GPU/hr Reserved NVL
CUDO UK	--	On request Custom
CambridgeNexus USA	--	On request Custom NVL
Civo UK	--	On request Custom NVL
Crusoe USA	--	On request Custom NVL
Hyperstack UK	--	On request Custom NVL