AMD MI300X
vs
Nvidia GB200
The GB200 has 51% more bandwidth, with about the same memory. The MI300X is typically cheaper.
At a glance
Memory
Within 5%
- MI300X
- 192 GB
- GB200
- 186 GB
Memory bandwidth
51% higher on GB200
- MI300X
- 5.30 TB/s
- GB200
- 8.00 TB/s
Cheapest on-demand
75% cheaper on MI300X
- MI300X
- $2.59 /GPU/hr
- GB200
- $10.50 /GPU/hr
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | MI300X | GB200 | Difference |
|---|---|---|---|
| On-demand | $4.43 /GPU/hr from $2.59 | $16.00 /GPU/hr from $10.50 | 72% cheaper on MI300X |
| Reserved | $2.81 /GPU/hr from $1.63 (12 mo) | -- /GPU/hr from $10.58 | |
| Spot | -- /GPU/hr from $1.76 | -- /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 spot on the MI300X 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
MI300X vs GB200 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | MI300X | GB200 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 192 GB HBM3 | 186 GB HBM3e | Within 5% |
| Bandwidth | 5,300 GB/s | 8,000 GB/s | 51% higher on GB200 |
| Bus width | 8,192-bit | ||
| Compute · dense | |||
| FP4 | Not supported | 10,000 TFLOPS | GB200 only |
| FP8 | 2,614.9 TFLOPS | 5,000 TFLOPS | 91% higher on GB200 |
| FP16 / BF16 | 1,307.4 TFLOPS | 2,500 TFLOPS | 91% higher on GB200 |
| INT8 | 2,614.9 TOPS | 5,000 TOPS | 91% higher on GB200 |
| FP32 | 163.4 TFLOPS | 80 TFLOPS | 2x higher on MI300X |
| FP64 | 81.7 TFLOPS | 40 TFLOPS | 2x higher on MI300X |
| Platform | |||
| Interconnect | Infinity Fabric 896 GB/s | NVLink 1,800 GB/s | 2x higher on GB200 |
| Board power | 750 W | 1,200 W | 60% higher on GB200 |
| Released | Q4 2023 | Q1 2024 | |
| Precision | |||
| Supported formats | FP8FP16BF16TF32FP32FP64INT8 | FP4FP6FP8FP16BF16TF32FP32FP64INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: MI300X datasheet and GB200 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 | GB200 |
|---|---|---|
|
|
On request Custom | On request Custom |
|
|
$6.00 /GPU/hr On-demand | $16.00 /GPU/hr On-demand NVL |
|
|
$7.86 /GPU/hr On-demand | $27.04 /GPU/hr On-demand |
|
|
On request Reserved | On request Custom NVL |
|
|
$2.59 /GPU/hr On-demand | -- |
|
|
$2.81 /GPU/hr On-demand | -- |
|
|
$3.12 /GPU/hr Reserved | -- |
|
|
On request Reserved | -- |
|
|
-- | $10.50 /GPU/hr On-demand NVL |
|
|
-- | $10.58 /GPU/hr Reserved |
|
|
-- | On request Custom NVL |
|
|
-- | On request Custom NVL |
11 providers list the MI300X and 10 the GB200. Every listing is on the MI300X page and the GB200 page.
Similar GPUs
Other comparisons in the same class.
Our data for AMD MI300X was last updated on Sept. 14, 2026, and for Nvidia GB200 on Sept. 14, 2026.