Intel Gaudi2
vs
Nvidia H100
Two data center GPUs, one Gaudi (2nd Gen) and one Hopper: 96 GB HBM2e against 80 GB HBM3 and 37% more memory bandwidth on the H100.
At a glance
Memory
- Gaudi2
- 96 GB
- H100
- 80 GB
1.2x more on Gaudi2
Memory bandwidth
- Gaudi2
- 2.45 TB/s
- H100
- 3.35 TB/s
1.4x higher on H100
Cheapest on-demand
- Gaudi2
- $1.03 /GPU/hr
- H100
- $1.41 /GPU/hr
27% cheaper on Gaudi2
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | Gaudi2 | H100 | Difference |
|---|---|---|---|
| On-demand | $1.21 /GPU/hr from $1.03 | $3.32 /GPU/hr from $1.41 | 2.7x more expensive on H100 |
| Reserved | -- /GPU/hr from $0.58 (12 mo) | $3.10 /GPU/hr from $1.53 (1 mo) | |
| Spot | No spot listings | $1.94 /GPU/hr from $0.02 |
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 on the Gaudi2: 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
Gaudi2 vs H100 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | Gaudi2 | H100 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 96 GB HBM2e | 80 GB HBM3 94 GB on NVL | 1.2x more on Gaudi2 |
| Bandwidth | 2,450 GB/s | 3,350 GB/s 2,000 GB/s on PCIe 3,938 GB/s on NVL | 1.4x higher on H100 |
| Bus width | 5,120-bit | ||
| Compute · dense | |||
| FP8 | 865 TFLOPS | 1,979 TFLOPS | 2.3x higher on H100 |
| FP16 / BF16 | 432 TFLOPS | 989.5 TFLOPS | 2.3x higher on H100 |
| INT8 | 1,979 TOPS | ||
| FP32 | 67 TFLOPS | ||
| FP64 | Not supported | 34 TFLOPS | H100 only |
| Platform | |||
| Interconnect | RoCE 600 GB/s | NVLink 900 GB/s NVLink 600 GB/s on PCIe, NVL | 1.5x higher on H100 |
| Board power | 600 W | 700 W | 1.2x higher on H100 |
| Released | Q2 2022 | Q3 2022 | |
| Precision | |||
| Supported formats | FP8FP16BF16TF32FP32INT8 | FP8FP16BF16TF32FP32FP64INT8 | |
Figures are for each model's headline configuration. Where a form factor carries a different number, it is named under the figure.
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: Gaudi2 datasheet and H100 datasheet.
Where to rent them
Providers listing these GPUs, those with both first, so you can switch without moving clouds.
| Provider | Gaudi2 /GPU/hr | H100 /GPU/hr |
|---|---|---|
Runcrate
|
On-Demand $1.21 | -- |
Sesterce
|
On-Demand $1.21 | -- |
Cyfuture AI
|
On-Demand $1.03 | -- |
Lium
|
-- | On-Demand $1.41 |
Vast.ai
|
-- | On-Demand $1.73 |
HyperAI
|
-- | On-Demand $1.80 |
UpCloud
|
-- | On-Demand $1.89 |
GPU.ai
|
-- | On-Demand $1.98 |
Koyeb
|
-- | On-Demand $2.50 |
Runpod
|
-- | On-Demand $2.59 |
Spheron
|
-- | On-Demand $2.65 |
3 providers list the Gaudi2 and 53 the H100. Every listing is on the Gaudi2 page and the H100 page.
Similar GPUs
Other comparisons in the same class.
-
Nvidia A100
From $0.47 /GPU/hr Compare -
AMD MI300X
From $2.39 /GPU/hr Compare -
Nvidia B300
From $6.50 /GPU/hr Compare -
Nvidia H200
From $2.09 /GPU/hr Compare -
Nvidia RTX 5090
From $0.35 /GPU/hr Compare
Our data for Intel Gaudi2 was last updated on Sept. 7, 2026, and for Nvidia H100 on Sept. 7, 2026.