Intel Gaudi2
vs
Nvidia RTX 5090
A data center GPU against a consumer card, one Gaudi (2nd Gen) and one Blackwell: 96 GB HBM2e against 32 GB GDDR7, 37% more memory bandwidth on the Gaudi2, and RoCE 600 GB/s on the Gaudi2 where the RTX 5090 is PCIe only.
At a glance
Memory
- Gaudi2
- 96 GB
- RTX 5090
- 32 GB
3x more on Gaudi2
Memory bandwidth
- Gaudi2
- 2.45 TB/s
- RTX 5090
- 1.79 TB/s
1.4x higher on Gaudi2
Cheapest on-demand
- Gaudi2
- $1.03 /GPU/hr
- RTX 5090
- $0.35 /GPU/hr
2.9x more expensive on Gaudi2
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | Gaudi2 | RTX 5090 | Difference |
|---|---|---|---|
| On-demand | $1.21 /GPU/hr from $1.03 | $0.66 /GPU/hr from $0.35 | 45% cheaper on RTX 5090 |
| Reserved | -- /GPU/hr from $0.58 (12 mo) | $0.58 /GPU/hr from $0.21 (1 mo) | |
| Spot | No spot listings | -- /GPU/hr from $0.15 |
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 and spot on the RTX 5090: 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 RTX 5090 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | Gaudi2 | RTX 5090 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 96 GB HBM2e | 32 GB GDDR7 | 3x more on Gaudi2 |
| Bandwidth | 2,450 GB/s | 1,792 GB/s | 1.4x higher on Gaudi2 |
| Bus width | 512-bit | ||
| Compute · dense | |||
| FP4 | Not supported | 1,676 TFLOPS | RTX 5090 only |
| FP8 | 865 TFLOPS | 419 TFLOPS | 2.1x higher on Gaudi2 |
| FP16 / BF16 | 432 TFLOPS | 209.5 TFLOPS | 2.1x higher on Gaudi2 |
| INT8 | 838 TOPS | ||
| FP32 | 104.8 TFLOPS | ||
| Platform | |||
| Interconnect | RoCE 600 GB/s | PCIe only | RoCE on Gaudi2 only |
| Board power | 600 W | 575 W | Within 5% |
| Released | Q2 2022 | Q1 2025 | 3 years newer on RTX 5090 |
| Precision | |||
| Supported formats | FP8FP16BF16TF32FP32INT8 | FP4FP8FP16BF16TF32FP32INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: Gaudi2 datasheet and RTX 5090 datasheet.
Where to rent them
Providers listing these GPUs, those with both first, so you can switch without moving clouds.
| Provider | Gaudi2 /GPU/hr | RTX 5090 /GPU/hr |
|---|---|---|
Runcrate
|
On-Demand $1.21 | -- |
Sesterce
|
On-Demand $1.21 | -- |
Cyfuture AI
|
On-Demand $1.03 | -- |
HyperAI
|
-- | On-Demand $0.35 |
GPU.ai
|
-- | On-Demand $0.40 |
GPUhub
|
-- | On-Demand $0.46 |
Vast.ai
|
-- | On-Demand $0.47 |
Salad
|
-- | On-Demand $0.50 |
Lium
|
-- | On-Demand $0.59 |
Nova Cloud
|
-- | On-Demand $0.63 |
Theta EdgeCloud
|
-- | On-Demand $0.77 |
3 providers list the Gaudi2 and 20 the RTX 5090. Every listing is on the Gaudi2 page and the RTX 5090 page.
Similar GPUs
Other comparisons in the same class.
-
Nvidia H100
From $1.73 /GPU/hr Compare -
Nvidia A100
From $0.47 /GPU/hr Compare -
AMD MI300X
From $2.39 /GPU/hr Compare -
Nvidia RTX PRO 6000
From $0.66 /GPU/hr Compare -
Nvidia RTX 4090
From $0.30 /GPU/hr Compare
Our data for Intel Gaudi2 was last updated on Sept. 7, 2026, and for Nvidia RTX 5090 on Sept. 7, 2026.