AMD MI300X
vs
Nvidia GH200
The MI300X has 2x the memory and 33% more bandwidth.
At a glance
Memory
2x more on MI300X
- MI300X
- 192 GB
- GH200
- 96 GB
Memory bandwidth
33% higher on MI300X
- MI300X
- 5.30 TB/s
- GH200
- 4.00 TB/s
Cheapest on-demand
13% cheaper on MI300X
- MI300X
- $2.59 /GPU/hr
- GH200
- $2.98 /GPU/hr
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | MI300X | GH200 | Difference |
|---|---|---|---|
| On-demand | $4.43 /GPU/hr from $2.59 | $3.87 /GPU/hr from $2.98 | 13% cheaper on GH200 |
| Reserved | $2.81 /GPU/hr from $1.63 (12 mo) | No reserved listings | |
| Spot | -- /GPU/hr from $1.76 | Sold out |
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: 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 GH200 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | MI300X | GH200 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 192 GB HBM3 | 96 GB HBM3 | 2x more on MI300X |
| Bandwidth | 5,300 GB/s | 4,000 GB/s | 33% higher on MI300X |
| Bus width | 8,192-bit | ||
| Compute · dense | |||
| FP8 | 2,614.9 TFLOPS | 1,979 TFLOPS | 32% higher on MI300X |
| FP16 / BF16 | 1,307.4 TFLOPS | 989.5 TFLOPS | 32% higher on MI300X |
| INT8 | 2,614.9 TOPS | 1,979 TOPS | 32% higher on MI300X |
| FP32 | 163.4 TFLOPS | 67 TFLOPS | 2.4x higher on MI300X |
| FP64 | 81.7 TFLOPS | 34 TFLOPS | 2.4x higher on MI300X |
| Platform | |||
| Interconnect | Infinity Fabric 896 GB/s | NVLink 900 GB/s | Within 5% |
| Released | Q4 2023 | Q2 2023 | 6 months newer on MI300X |
| Precision | |||
| Supported formats | FP8FP16BF16TF32FP32FP64INT8 | FP8FP16BF16TF32FP32FP64INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: MI300X datasheet and GH200 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 | GH200 |
|---|---|---|
Denvr
Canada
|
On request Custom | $3.87 /GPU/hr On-demand |
DigitalOcean
USA
|
$2.59 /GPU/hr On-demand | -- |
Cyfuture AI
India
|
$2.81 /GPU/hr On-demand | -- |
Oracle Cloud
USA
|
$6.00 /GPU/hr On-demand | -- |
Azure
USA
|
$7.86 /GPU/hr On-demand | -- |
Cirrascale
USA
|
$3.12 /GPU/hr Reserved | -- |
Crusoe
USA
|
On request Reserved | -- |
Runpod
USA
|
On request Reserved | -- |
Runcrate
USA
|
-- | $2.98 /GPU/hr On-demand SXM |
CoreWeave
USA
|
-- | $6.50 /GPU/hr On-demand |
Lambda Labs
USA
|
-- | $2.29 /GPU/hr On-demand |
Sesterce
France
|
-- | $2.52 /GPU/hr On-demand |
Vultr
USA
|
-- | $1.99 /GPU/hr Spot |
11 providers list the MI300X and 6 the GH200. Every listing is on the MI300X page and the GH200 page.
Similar GPUs
Other comparisons in the same class.
Our data for AMD MI300X was last updated on Sept. 14, 2026, and for Nvidia GH200 on Sept. 14, 2026.