AMD MI350X
vs
Nvidia L40
The MI350X is newer, with 6x the memory and 9.3x the bandwidth. 1 provider lists it, against 13 for the L40.
At a glance
Memory
6x more on MI350X
- MI350X
- 288 GB
- L40
- 48 GB
Memory bandwidth
9.3x higher on MI350X
- MI350X
- 8,000 GB/s
- L40
- 864 GB/s
Cheapest on-demand
MI350X is not sold on demand
- MI350X
- --
- L40
- $0.47 /GPU/hr
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | MI350X | L40 | Difference |
|---|---|---|---|
| On-demand | No on-demand listings | $1.06 /GPU/hr from $0.47 | |
| Reserved | -- /GPU/hr from $4.76 (12 mo) | -- /GPU/hr from $0.70 | |
| Spot | -- /GPU/hr from $2.46 | $0.78 /GPU/hr from $0.41 |
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 reserved and spot on the MI350X and reserved on the L40: 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
MI350X vs L40 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | MI350X | L40 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 288 GB HBM3e | 48 GB GDDR6 | 6x more on MI350X |
| Bandwidth | 8,000 GB/s | 864 GB/s | 9.3x higher on MI350X |
| Bus width | 8,192-bit | 384-bit | 21x wider on MI350X |
| Compute · dense | |||
| FP4 | 9,227.5 TFLOPS | Not supported | MI350X only |
| FP8 | 4,614 TFLOPS | 362 TFLOPS | 13x higher on MI350X |
| FP16 / BF16 | 2,309.6 TFLOPS | 181.1 TFLOPS | 13x higher on MI350X |
| INT8 | 4,614 TOPS | 362 TOPS | 13x higher on MI350X |
| FP32 | 144.2 TFLOPS | 90.5 TFLOPS | 59% higher on MI350X |
| FP64 | 72.1 TFLOPS | Not supported | MI350X only |
| Platform | |||
| Interconnect | Infinity Fabric 1,075 GB/s | PCIe only | Infinity Fabric on MI350X only |
| Board power | 1,000 W | 300 W | 3.3x higher on MI350X |
| Released | Q2 2025 | Q4 2022 | 3 years newer on MI350X |
| Precision | |||
| Supported formats | FP4FP6FP8FP16BF16FP32FP64INT8 | FP8FP16BF16TF32FP32INT4INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: MI350X datasheet and L40 datasheet.
Where to rent them
Providers that rent these GPUs, with each one's cheapest rate. No provider we track offers both right now.
| Provider | MI350X | L40 |
|---|---|---|
DigitalOcean
USA
|
$4.76 /GPU/hr Reserved | -- |
Vast.ai
USA
|
-- | $0.47 /GPU/hr On-demand |
GPU.ai
UAE
|
-- | $0.58 /GPU/hr On-demand |
Thunder Compute
USA
|
-- | $0.79 /GPU/hr On-demand |
Massed Compute
USA
|
-- | $0.86 /GPU/hr On-demand |
Sesterce
France
|
-- | $0.97 /GPU/hr On-demand |
Hyperstack
UK
|
-- | $1.00 /GPU/hr On-demand |
Oblivus
USA
|
-- | $1.05 /GPU/hr On-demand PCIe |
Spheron
Singapore
|
-- | $1.06 /GPU/hr On-demand PCIe |
1 provider list the MI350X and 13 the L40. Every listing is on the MI350X page and the L40 page.
Similar GPUs
Other comparisons in the same class.
Our data for AMD MI350X was last updated on Sept. 14, 2026, and for Nvidia L40 on Sept. 14, 2026.