AMD MI300X
vs
Nvidia L40S
Two data center GPUs, one CDNA 3 and one Ada Lovelace: 192 GB HBM3 against 48 GB GDDR6, 6.1x the memory bandwidth on the MI300X, and Infinity Fabric 896 GB/s on the MI300X where the L40S is PCIe only.
At a glance
Updated 3 minutes ago- Memory
- 192 GB
- HBM3
- Memory bandwidth
- 5.30 TB/s
- From
- $2.39 /GPU/hr
- 10 providers
- Memory
- 48 GB
- GDDR6
- Memory bandwidth
- 864 GB/s
- From
- $0.38 /GPU/hr
- 36 providers
Price comparison
Cheapest listed price per GPU per hour by billing type, and the median across providers.
| Billing | MI300X | L40S | Difference |
|---|---|---|---|
| On-demand | $2.39 | $0.38 | 6.3x more expensive on MI300X |
| Spot | $1.60 | $0.47 | 3.4x more expensive on MI300X |
| Reserved | $1.61 | $0.60 | 2.7x more expensive on MI300X |
| Median | $2.91 | $1.28 | 2.3x 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 L40S price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | MI300X | L40S | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 192 GB HBM3 | 48 GB GDDR6 | 4x more on MI300X |
| Bandwidth | 5,300 GB/s | 864 GB/s | 6.1x higher on MI300X |
| Bus width | 8,192-bit | 384-bit | 21x wider on MI300X |
| Compute · dense | |||
| FP8 | 2,614.9 TFLOPS | 733 TFLOPS | 3.6x higher on MI300X |
| FP16 / BF16 | 1,307.4 TFLOPS | 362.1 TFLOPS | 3.6x higher on MI300X |
| INT8 | 2,614.9 TOPS | 733 TOPS | 3.6x higher on MI300X |
| FP32 | 163.4 TFLOPS | 91.6 TFLOPS | 1.8x 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 | 350 W | 2.1x higher on MI300X |
| Released | Q4 2023 | Q3 2023 | |
| Precision | |||
| Supported formats | FP8FP16BF16TF32FP32FP64INT8 | FP8FP16BF16TF32FP32INT4INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: MI300X datasheet and L40S datasheet.
Where to rent them
Providers listing these GPUs, those with both first, so you can switch without moving clouds.
| Provider | MI300X /GPU/hr | L40S /GPU/hr |
|---|---|---|
Runpod
|
On-Demand $2.39 | On-Demand $0.79 |
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 | -- |
Lium
|
-- | On-Demand $0.38 |
Novita
|
-- | On-Demand $0.55 |
Vast.ai
|
-- | On-Demand $0.60 |
GPU.ai
|
-- | On-Demand $0.79 |
EmpirioLabs AI
|
-- | On-Demand $0.80 |
Packet·ai
|
-- | On-Demand $0.92 |
Sesterce
|
-- | On-Demand $0.97 |
10 providers list the MI300X and 36 the L40S. Every listing is on the MI300X page and the L40S page.
Similar GPUs
Other comparisons in the same class.
Our data for AMD MI300X was last updated on Sept. 7, 2026, and for Nvidia L40S on Sept. 7, 2026.