Intel Gaudi 2
vs
Nvidia L40S
The Gaudi 2 has 2x the memory and 2.8x the bandwidth. The L40S is newer and cheaper right now.
At a glance
Memory
2x more on Gaudi 2
- Gaudi 2
- 96 GB
- L40S
- 48 GB
Memory bandwidth
2.8x higher on Gaudi 2
- Gaudi 2
- 2,450 GB/s
- L40S
- 864 GB/s
Cheapest on-demand
46% cheaper on L40S
- Gaudi 2
- $1.02 /GPU/hr
- L40S
- $0.55 /GPU/hr
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | Gaudi 2 | L40S | Difference |
|---|---|---|---|
| On-demand | -- /GPU/hr from $1.02 | $1.50 /GPU/hr from $0.55 | |
| Reserved | -- /GPU/hr from $0.58 (12 mo) | $1.10 /GPU/hr from $0.60 (12 mo) | |
| Spot | No spot listings | $0.98 /GPU/hr from $0.59 |
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 on-demand and reserved on the Gaudi 2: 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
Gaudi 2 vs L40S price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | Gaudi 2 | L40S | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 96 GB HBM2e | 48 GB GDDR6 | 2x more on Gaudi 2 |
| Bandwidth | 2,450 GB/s | 864 GB/s | 2.8x higher on Gaudi 2 |
| Bus width | 384-bit | ||
| Compute · dense | |||
| FP8 | 865 TFLOPS | 733 TFLOPS | 18% higher on Gaudi 2 |
| FP16 / BF16 | 432 TFLOPS | 362.1 TFLOPS | 19% higher on Gaudi 2 |
| INT8 | 733 TOPS | ||
| FP32 | 91.6 TFLOPS | ||
| Platform | |||
| Interconnect | RoCE 600 GB/s | PCIe only | RoCE on Gaudi 2 only |
| Board power | 600 W | 350 W | 71% higher on Gaudi 2 |
| Released | Q2 2022 | Q3 2023 | 15 months newer on L40S |
| Precision | |||
| Supported formats | FP8FP16BF16TF32FP32INT8 | FP8FP16BF16TF32FP32INT4INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: Gaudi 2 datasheet and L40S datasheet.
Where to rent them
Providers that rent these GPUs, with each one's cheapest rate. Providers that rent both are listed first.
| Provider | Gaudi 2 | L40S |
|---|---|---|
Sesterce
France
|
$1.21 /GPU/hr On-demand | $0.97 /GPU/hr On-demand |
Cyfuture AI
India
|
$1.02 /GPU/hr On-demand | -- |
Denvr
Canada
|
$1.25 /GPU/hr On-demand | -- |
Novita
USA
|
-- | $0.55 /GPU/hr On-demand |
Vast.ai
USA
|
-- | $0.62 /GPU/hr On-demand |
GPU.ai
UAE
|
-- | $0.79 /GPU/hr On-demand |
Runpod
USA
|
-- | $0.79 /GPU/hr On-demand |
Packet·ai
USA
|
-- | $0.92 /GPU/hr On-demand |
Massed Compute
USA
|
-- | $0.97 /GPU/hr On-demand |
Runcrate
USA
|
-- | $1.14 /GPU/hr On-demand PCIe |
3 providers list the Gaudi 2 and 39 the L40S. Every listing is on the Gaudi 2 page and the L40S page.
Similar GPUs
Other comparisons in the same class.
-
Nvidia H100
80 GB HBM3 · 37% more bandwidth than the Gaudi 2
From $1.30 /GPU/hr Compare
-
Nvidia A100
80 GB HBM2e · 21% less bandwidth than the Gaudi 2
From $0.40 /GPU/hr Compare
-
AMD MI300X
192 GB HBM3 · 2.2x the bandwidth of the Gaudi 2
From $2.59 /GPU/hr Compare
Our data for Intel Gaudi 2 was last updated on Sept. 23, 2026, and for Nvidia L40S on Sept. 14, 2026.