AMD MI300X
vs
Nvidia RTX 5060
A data center GPU against a consumer card, one CDNA 3 and one Blackwell: 192 GB HBM3 against 8 GB GDDR7, 12x the memory bandwidth on the MI300X, and Infinity Fabric 896 GB/s on the MI300X where the RTX 5060 is PCIe only.
At a glance
Updated 6 minutes ago- Memory
- 192 GB
- HBM3
- Memory bandwidth
- 5.30 TB/s
- From
- $2.39 /GPU/hr
- 10 providers
- Memory
- 8 GB
- GDDR7
- Memory bandwidth
- 448 GB/s
- From
- $0.09 /GPU/hr
- 4 providers
Price comparison
Cheapest listed price per GPU per hour by billing type, and the median across providers.
| Billing | MI300X | RTX 5060 | Difference |
|---|---|---|---|
| On-demand | $2.39 | $0.09 | 25x more expensive on MI300X |
| Spot | $1.60 | $0.04 | 40x more expensive on MI300X |
| Reserved | $1.61 | $0.08 | 19x more expensive on MI300X |
| Median | $2.91 | $0.14 | 21x more expensive on MI300X |
Median: Median across providers, one vote each, so a large catalog does not outweigh a small one.
Price history
MI300X vs RTX 5060 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | MI300X | RTX 5060 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 192 GB HBM3 | 8 GB GDDR7 | 24x more on MI300X |
| Bandwidth | 5,300 GB/s | 448 GB/s | 12x higher on MI300X |
| Bus width | 8,192-bit | 128-bit | 64x wider on MI300X |
| Compute · dense | |||
| FP4 | Not supported | 307 TFLOPS | RTX 5060 only |
| FP8 | 2,614.9 TFLOPS | 76.8 TFLOPS | 34x higher on MI300X |
| FP16 / BF16 | 1,307.4 TFLOPS | 38.4 TFLOPS | 34x higher on MI300X |
| INT8 | 2,614.9 TOPS | 153.6 TOPS | 17x higher on MI300X |
| FP32 | 163.4 TFLOPS | 19.2 TFLOPS | 8.5x higher on MI300X |
| FP64 | 81.7 TFLOPS | Not supported | MI300X only |
| Platform | |||
| Interconnect | Infinity Fabric 896 GB/s | PCIe only | Infinity Fabric on MI300X only |
| Board power | 750 W | 145 W | 5.2x higher on MI300X |
| Released | Q4 2023 | Q2 2025 | 2 years newer on RTX 5060 |
| Precision | |||
| Supported formats | FP8FP16BF16TF32FP32FP64INT8 | FP4FP8FP16BF16TF32FP32INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: MI300X datasheet and RTX 5060 datasheet.
Where to rent them
Providers listing these GPUs, those with both first, so you can switch without moving clouds.
| Provider | MI300X /GPU/hr | RTX 5060 /GPU/hr |
|---|---|---|
Runpod
|
On-Demand $2.39 | -- |
DigitalOcean
|
On-Demand $2.59 | -- |
Cyfuture AI
|
On-Demand $2.78 | -- |
Hot Aisle
|
On-Demand $2.99 | -- |
Oracle Cloud
|
On-Demand $6.00 | -- |
Azure
|
On-Demand $7.86 | -- |
Cirrascale
|
Reserved (12mo) $3.12 | -- |
Crusoe
|
Reservation on request | -- |
Vast.ai
|
-- | On-Demand $0.09 |
Salad
|
-- | On-Demand $0.14 |
Theta EdgeCloud
|
-- | On-Demand $0.18 |
Database Mart
|
-- | Reserved (24mo) $0.12 |
10 providers list the MI300X and 4 the RTX 5060. Every listing is on the MI300X page and the RTX 5060 page.
Similar GPUs
Other comparisons in the same class.
Our data for AMD MI300X was last updated on Sept. 7, 2026, and for Nvidia RTX 5060 on Sept. 7, 2026.