Intel Gaudi2
vs
Nvidia GB300
The GB300 is newer, with 3x the memory and 3.3x the bandwidth. The Gaudi2 is cheaper right now.
At a glance
Memory
3x more on GB300
- Gaudi2
- 96 GB
- GB300
- 288 GB
Memory bandwidth
3.3x higher on GB300
- Gaudi2
- 2.45 TB/s
- GB300
- 8.00 TB/s
Cheapest on-demand
94% cheaper on Gaudi2
- Gaudi2
- $1.03 /GPU/hr
- GB300
- $18.00 /GPU/hr
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | Gaudi2 | GB300 | Difference |
|---|---|---|---|
| On-demand | $1.21 /GPU/hr from $1.03 | -- /GPU/hr from $18.00 | |
| Reserved | -- /GPU/hr from $0.58 (12 mo) | On request | |
| 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 on-demand on the GB300: 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 GB300 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | Gaudi2 | GB300 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 96 GB HBM2e | 288 GB HBM3e | 3x more on GB300 |
| Bandwidth | 2,450 GB/s | 8,000 GB/s | 3.3x higher on GB300 |
| Bus width | 8,192-bit | ||
| Compute · dense | |||
| FP4 | Not supported | 15,000 TFLOPS | GB300 only |
| FP8 | 865 TFLOPS | 5,000 TFLOPS | 5.8x higher on GB300 |
| FP16 / BF16 | 432 TFLOPS | 2,500 TFLOPS | 5.8x higher on GB300 |
| INT8 | 165 TOPS | ||
| FP32 | 80 TFLOPS | ||
| FP64 | Not supported | 1.3 TFLOPS | GB300 only |
| Platform | |||
| Interconnect | RoCE 600 GB/s | NVLink 1,800 GB/s | 3x higher on GB300 |
| Board power | 600 W | 1,400 W | 2.3x higher on GB300 |
| Released | Q2 2022 | Q1 2025 | 3 years newer on GB300 |
| Precision | |||
| Supported formats | FP8FP16BF16TF32FP32INT8 | FP4FP6FP8FP16BF16TF32FP32FP64INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: Gaudi2 datasheet and GB300 datasheet.
Where to rent them
Providers that rent these GPUs, with each one's cheapest rate. No provider we track offers both right now.
| Provider | Gaudi2 | GB300 |
|---|---|---|
Runcrate
USA
|
$1.21 /GPU/hr On-demand PCIe | -- |
Sesterce
France
|
$1.21 /GPU/hr On-demand | -- |
Cyfuture AI
India
|
$1.03 /GPU/hr On-demand | -- |
Denvr
Canada
|
$1.25 /GPU/hr On-demand | -- |
Oracle Cloud
USA
|
-- | $18.00 /GPU/hr On-demand NVL |
AWS
USA
|
-- | On request Reserved |
CoreWeave
USA
|
-- | On request Custom NVL |
Gcore
Luxembourg
|
-- | On request Custom NVL |
Nebius
Netherlands
|
-- | On request Custom NVL |
Together AI
USA
|
-- | On request Custom NVL |
Verda
Finland
|
-- | $9.25 /GPU/hr On-demand SXM |
Similar GPUs
Other comparisons in the same class.
-
Nvidia H100
80 GB HBM3 · 37% more bandwidth than the Gaudi2
From $1.30 /GPU/hr Compare
-
Nvidia A100
80 GB HBM2e · 21% less bandwidth than the Gaudi2
From $0.40 /GPU/hr Compare
-
AMD MI300X
192 GB HBM3 · 2.2x the bandwidth of the Gaudi2
From $2.59 /GPU/hr Compare -
Nvidia B300
288 GB HBM3e · released Q1 2025
From $6.50 /GPU/hr Compare
-
Nvidia B200
180 GB HBM3e · released Q1 2024
From $3.75 /GPU/hr Compare
Our data for Intel Gaudi2 was last updated on Sept. 14, 2026, and for Nvidia GB300 on Sept. 14, 2026.