The GB300 is newer, with 7.2x the memory and 5.1x the bandwidth. The A800 is cheaper right now.
At a glance
Memory
7.2x more on GB300
- A800
- 40 GB
- GB300
- 288 GB
Memory bandwidth
5.1x higher on GB300
- A800
- 1.55 TB/s
- GB300
- 8.00 TB/s
Cheapest on-demand
93% cheaper on A800
- A800
- $1.18 /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 | A800 | GB300 | Difference |
|---|---|---|---|
| On-demand | -- /GPU/hr from $1.18 | -- /GPU/hr from $18.00 | |
| Reserved | No reserved listings | 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 on-demand on the A800 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
A800 vs GB300 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | A800 | GB300 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 40 GB HBM2 | 288 GB HBM3e | 7.2x more on GB300 |
| Bandwidth | 1,555 GB/s | 8,000 GB/s | 5.1x higher on GB300 |
| Bus width | 5,120-bit | 8,192-bit | 60% wider on GB300 |
| Compute · dense | |||
| FP4 | Not supported | 15,000 TFLOPS | GB300 only |
| FP8 | Not supported | 5,000 TFLOPS | GB300 only |
| FP16 / BF16 | 312 TFLOPS | 2,500 TFLOPS | 8x higher on GB300 |
| INT8 | 623.5 TOPS | 165 TOPS | 3.8x higher on A800 |
| FP32 | 19.5 TFLOPS | 80 TFLOPS | 4.1x higher on GB300 |
| FP64 | 9.7 TFLOPS | 1.3 TFLOPS | 7.5x higher on A800 |
| Platform | |||
| Interconnect | NVLink 400 GB/s | NVLink 1,800 GB/s | 4.5x higher on GB300 |
| Board power | 240 W | 1,400 W | 5.8x higher on GB300 |
| Released | Q4 2022 | Q1 2025 | 2 years newer on GB300 |
| Precision | |||
| Supported formats | FP16BF16TF32FP32FP64INT4INT8 | FP4FP6FP8FP16BF16TF32FP32FP64INT8 | |
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: A800 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 | A800 | GB300 |
|---|---|---|
GPUhub
Singapore
|
$1.18 /GPU/hr On-demand NVL | -- |
GPUaaS
USA
|
-- | $5.00 /GPU/hr Custom NVL |
Orion AI Factory
Serbia
|
-- | On request Reserved NVL |
CambridgeNexus
USA
|
-- | On request Custom NVL |
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 |
1 provider list the A800 and 10 the GB300. Every listing is on the A800 page and the GB300 page.
Similar GPUs
Other comparisons in the same class.
Our data for Nvidia A800 was last updated on Sept. 14, 2026, and for Nvidia GB300 on Sept. 14, 2026.