AMD MI350X
vs
Nvidia L40S
Two data center GPUs, one CDNA 4 and one Ada Lovelace: 288 GB HBM3e against 48 GB GDDR6, 9.3x the memory bandwidth on the MI350X, and Infinity Fabric 1,075 GB/s on the MI350X where the L40S is PCIe only.
At a glance
Memory
- MI350X
- 288 GB
- L40S
- 48 GB
6x more on MI350X
Memory bandwidth
- MI350X
- 8,000 GB/s
- L40S
- 864 GB/s
9.3x higher on MI350X
Cheapest on-demand
- MI350X
- --
- L40S
- $0.38 /GPU/hr
MI350X is not sold on demand
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | MI350X | L40S | Difference |
|---|---|---|---|
| On-demand | No on-demand listings | $1.44 /GPU/hr from $0.38 | |
| Reserved | -- /GPU/hr from $4.76 (12 mo) | $1.11 /GPU/hr from $0.37 (3 mo) | |
| Spot | -- /GPU/hr from $4.00 | $0.90 /GPU/hr from $0.27 |
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: 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 L40S price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | MI350X | L40S | 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 | 733 TFLOPS | 6.3x higher on MI350X |
| FP16 / BF16 | 2,309.6 TFLOPS | 362.1 TFLOPS | 6.4x higher on MI350X |
| INT8 | 4,614 TOPS | 733 TOPS | 6.3x higher on MI350X |
| FP32 | 144.2 TFLOPS | 91.6 TFLOPS | 1.6x 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 | 350 W | 2.9x higher on MI350X |
| Released | Q2 2025 | Q3 2023 | 2 years newer on MI350X |
| Precision | |||
| Supported formats | FP4FP6FP8FP16BF16FP32FP64INT8 | FP8FP16BF16TF32FP32INT4INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: MI350X datasheet and L40S datasheet.
Where to rent them
Providers listing these GPUs, those with both first, so you can switch without moving clouds.
| Provider | MI350X /GPU/hr | L40S /GPU/hr |
|---|---|---|
DigitalOcean
|
Reserved (12mo) $4.76 | -- |
Lium
|
-- | On-Demand $0.38 |
Vast.ai
|
-- | On-Demand $0.53 |
GPU.ai
|
-- | On-Demand $0.54 |
Novita
|
-- | On-Demand $0.55 |
Runpod
|
-- | On-Demand $0.79 |
EmpirioLabs AI
|
-- | On-Demand $0.80 |
Packet·ai
|
-- | On-Demand $0.92 |
Sesterce
|
-- | On-Demand $0.97 |
1 provider list the MI350X and 36 the L40S. Every listing is on the MI350X page and the L40S page.
Similar GPUs
Other comparisons in the same class.
-
Nvidia B200
180 GB HBM3e · released Q1 2024
From $3.75 /GPU/hr Compare
-
Nvidia H200
141 GB HBM3e · 40% less bandwidth than the MI350X
From $2.09 /GPU/hr Compare
-
AMD MI355X
288 GB HBM3e · released Q2 2025
From $8.60 /GPU/hr Compare
-
Nvidia H100
80 GB HBM3 · 3.9x the bandwidth of the L40S
From $1.25 /GPU/hr Compare
-
Nvidia A100
80 GB HBM2e · 2.2x the bandwidth of the L40S
From $0.40 /GPU/hr Compare
Our data for AMD MI350X was last updated on Sept. 14, 2026, and for Nvidia L40S on Sept. 14, 2026.