Intel Gaudi 3
vs
Nvidia A40
The Gaudi 3 is newer, with 2.7x the memory and 5.3x the bandwidth.
At a glance
Memory
2.7x more on Gaudi 3
- Gaudi 3
- 128 GB
- A40
- 48 GB
Memory bandwidth
5.3x higher on Gaudi 3
- Gaudi 3
- 3,700 GB/s
- A40
- 696 GB/s
Cheapest on-demand
- Gaudi 3
- --
- A40
- $0.34 /GPU/hr
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | Gaudi 3 | A40 | Difference |
|---|---|---|---|
| On-demand | No on-demand listings | $1.00 /GPU/hr from $0.34 | |
| Reserved | No reserved listings | -- /GPU/hr from $0.61 (24 mo) | |
| Spot | No spot listings | -- /GPU/hr from $0.32 |
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 and spot on the A40: 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 3 vs A40 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | Gaudi 3 | A40 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 128 GB HBM2e | 48 GB GDDR6 | 2.7x more on Gaudi 3 |
| Bandwidth | 3,700 GB/s | 696 GB/s | 5.3x higher on Gaudi 3 |
| Bus width | 384-bit | ||
| Compute · dense | |||
| FP8 | 1,678 TFLOPS | Not supported | Gaudi 3 only |
| FP16 / BF16 | 1,678 TFLOPS | 149.7 TFLOPS | 11x higher on Gaudi 3 |
| INT8 | Not supported | 299.3 TOPS | A40 only |
| FP32 | 37.4 TFLOPS | ||
| Platform | |||
| Interconnect | RoCE 1,200 GB/s | PCIe only | RoCE on Gaudi 3 only |
| Board power | 900 W | 300 W | 3x higher on Gaudi 3 |
| Released | Q2 2024 | Q4 2020 | 4 years newer on Gaudi 3 |
| Precision | |||
| Supported formats | FP8FP16BF16TF32FP32 | FP16BF16TF32FP32INT4INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: Gaudi 3 datasheet and A40 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 | Gaudi 3 | A40 |
|---|---|---|
Vast.ai
USA
|
-- | $0.34 /GPU/hr On-demand |
GPU.ai
UAE
|
-- | $0.49 /GPU/hr On-demand |
Runpod
USA
|
-- | $0.49 /GPU/hr On-demand |
Sesterce
France
|
-- | $2.05 /GPU/hr On-demand |
Runcrate
USA
|
-- | $2.05 /GPU/hr On-demand PCIe |
Denvr
Canada
|
-- | $0.65 /GPU/hr On-demand |
Exoscale
Switzerland
|
-- | $1.05 /GPU/hr On-demand |
Database Mart
USA
|
-- | $0.61 /GPU/hr Reserved |
0 providers list the Gaudi 3 and 10 the A40. Every listing is on the Gaudi 3 page and the A40 page.
Similar GPUs
Other comparisons in the same class.
-
Nvidia H100
80 GB HBM3 · released Q3 2022
From $1.30 /GPU/hr Compare
-
Nvidia H200
141 GB HBM3e · 30% more bandwidth than the Gaudi 3
From $2.09 /GPU/hr Compare
-
AMD MI300X
192 GB HBM3 · 43% more bandwidth than the Gaudi 3
From $2.59 /GPU/hr Compare -
Nvidia RTX 6000 Ada
48 GB GDDR6 · 38% more bandwidth than the A40
From $0.48 /GPU/hr Compare
-
Nvidia L40
48 GB GDDR6 · 24% more bandwidth than the A40
From $0.46 /GPU/hr Compare
Our data for Intel Gaudi 3 was last updated on Sept. 23, 2026, and for Nvidia A40 on Sept. 14, 2026.