Intel Gaudi2
vs
Nvidia RTX 6000 Ada
A data center GPU against a workstation card, one Gaudi (2nd Gen) and one Ada Lovelace: 96 GB HBM2e against 48 GB GDDR6, 2.6x the memory bandwidth on the Gaudi2, and RoCE 600 GB/s on the Gaudi2 where the RTX 6000 Ada is PCIe only.
At a glance
Memory
- Gaudi2
- 96 GB
- RTX 6000 Ada
- 48 GB
2x more on Gaudi2
Memory bandwidth
- Gaudi2
- 2,450 GB/s
- RTX 6000 Ada
- 960 GB/s
2.6x higher on Gaudi2
Cheapest on-demand
- Gaudi2
- $1.03 /GPU/hr
- RTX 6000 Ada
- $0.86 /GPU/hr
16% cheaper on RTX 6000 Ada
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | Gaudi2 | RTX 6000 Ada | Difference |
|---|---|---|---|
| On-demand | $1.21 /GPU/hr from $1.03 | $1.23 /GPU/hr from $0.86 | Within 5% |
| Reserved | -- /GPU/hr from $0.58 (12 mo) | -- /GPU/hr from $1.04 (12 mo) | |
| Spot | No spot listings | Sold out |
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 reserved on the RTX 6000 Ada: 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 6000 Ada price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | Gaudi2 | RTX 6000 Ada | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 96 GB HBM2e | 48 GB GDDR6 | 2x more on Gaudi2 |
| Bandwidth | 2,450 GB/s | 960 GB/s | 2.6x higher on Gaudi2 |
| Bus width | 384-bit | ||
| Compute · dense | |||
| FP8 | 865 TFLOPS | 728.5 TFLOPS | 1.2x higher on Gaudi2 |
| FP16 / BF16 | 432 TFLOPS | 364.2 TFLOPS | 1.2x higher on Gaudi2 |
| FP32 | 91.1 TFLOPS | ||
| Platform | |||
| Interconnect | RoCE 600 GB/s | PCIe only | RoCE on Gaudi2 only |
| Board power | 600 W | 300 W | 2x higher on Gaudi2 |
| Released | Q2 2022 | Q4 2022 | 7 months newer on RTX 6000 Ada |
| Precision | |||
| Supported formats | FP8FP16BF16TF32FP32INT8 | FP8FP16BF16TF32FP32INT4INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: Gaudi2 datasheet and RTX 6000 Ada 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 6000 Ada /GPU/hr |
|---|---|---|
Sesterce
|
On-Demand $1.21 | On-Demand $0.66 |
Runcrate
|
On-Demand $1.21 | -- |
Cyfuture AI
|
On-Demand $1.03 | -- |
TensorDock
|
-- | On-Demand $0.86 |
SwissGPU
|
-- | On-Demand $1.23 |
DigitalOcean
|
-- | On-Demand $1.57 |
AceCloud
|
-- | Reserved (12mo) $1.04 |
Runpod
|
-- | Reservation on request |
Novita
|
-- | On-Demand $0.77 |
Massed Compute
|
-- | On-Demand $0.79 |
3 providers list the Gaudi2 and 10 the RTX 6000 Ada. Every listing is on the Gaudi2 page and the RTX 6000 Ada page.
Similar GPUs
Other comparisons in the same class.
-
Nvidia H100
From $1.55 /GPU/hr Compare -
Nvidia A100
From $0.80 /GPU/hr Compare -
AMD MI300X
From $2.39 /GPU/hr Compare -
Nvidia L40S
From $0.55 /GPU/hr Compare -
Nvidia RTX A6000
From $0.35 /GPU/hr Compare
Our data for Intel Gaudi2 was last updated on Sept. 7, 2026, and for Nvidia RTX 6000 Ada on Sept. 7, 2026.