AMD MI300X
vs
Nvidia Vera Rubin
The Vera Rubin is newer, with 50% more memory and 3.6x the bandwidth.
At a glance
Memory
50% more on Vera Rubin
- MI300X
- 192 GB
- Vera Rubin
- 288 GB
Memory bandwidth
3.6x higher on Vera Rubin
- MI300X
- 5.30 TB/s
- Vera Rubin
- 19.20 TB/s
Cheapest on-demand
Vera Rubin is not sold on demand
- MI300X
- $2.59 /GPU/hr
- Vera Rubin
- --
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | MI300X | Vera Rubin | Difference |
|---|---|---|---|
| On-demand | $2.87 /GPU/hr from $2.59 | No on-demand listings | |
| Reserved | $2.20 /GPU/hr from $1.64 (12 mo) | -- /GPU/hr | |
| Spot | -- /GPU/hr from $1.84 | 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 spot on the MI300X and 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
MI300X vs Vera Rubin price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | MI300X | Vera Rubin | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 192 GB HBM3 | 288 GB HBM4 | 50% more on Vera Rubin |
| Bandwidth | 5,300 GB/s | 19,200 GB/s | 3.6x 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 MI300X |
| FP32 | 163.4 TFLOPS | 130 TFLOPS | 26% higher on MI300X |
| FP64 | 81.7 TFLOPS | 33 TFLOPS | 2.5x higher on MI300X |
| Platform | |||
| Interconnect | Infinity Fabric 896 GB/s | NVLink 3,000 GB/s | 3.3x higher on Vera Rubin |
| Released | Q4 2023 | Q1 2026 | 2 years newer on Vera Rubin |
| Precision | |||
| Supported formats | FP8FP16BF16TF32FP32FP64INT8 | FP4FP6FP8FP16BF16TF32FP32FP64INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: MI300X datasheet and Vera Rubin datasheet.
Where to rent them
Providers that rent these GPUs, with each one's cheapest rate. Providers that rent both are listed first.
| Provider | MI300X | Vera Rubin |
|---|---|---|
|
|
On request Reserved | On request Custom NVL |
|
|
On request Custom | -- |
|
|
$2.59 /GPU/hr On-demand | -- |
|
|
$2.62 /GPU/hr On-demand | -- |
|
|
$2.83 /GPU/hr On-demand | -- |
|
|
$6.00 /GPU/hr On-demand | -- |
|
|
$7.86 /GPU/hr On-demand | -- |
|
|
On request Reserved | -- |
|
|
-- | $11.05 /GPU/hr Reserved NVL |
|
|
-- | On request Custom |
|
|
-- | On request Custom NVL |
|
|
-- | On request Custom NVL |
|
|
-- | On request Custom NVL |
12 providers list the MI300X and 6 the Vera Rubin. Every listing is on the MI300X page and the Vera Rubin page.
Similar GPUs
Other comparisons in the same class.
-
-
-
-
Nvidia B300
288 GB HBM3e · 58% less bandwidth than the Vera Rubin
On-demand from $5.57 /GPU/hr -
Nvidia GB300
288 GB HBM3e · 58% less bandwidth than the Vera Rubin
On-demand from $18.00 /GPU/hr
Our data for AMD MI300X was last updated on Sept. 14, 2026, and for Nvidia Vera Rubin on Nov. 9, 2026.