The H800 is newer, with 5x the memory and 4.5x the bandwidth.
At a glance
Memory
5x more on H800
- A4000
- 16 GB
- H800
- 80 GB
Memory bandwidth
4.5x higher on H800
- A4000
- 448 GB/s
- H800
- 2,000 GB/s
Cheapest on-demand
- A4000
- $0.07 /GPU/hr
- H800
- --
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | A4000 | H800 | Difference |
|---|---|---|---|
| On-demand | $0.21 /GPU/hr from $0.07 | No on-demand listings | |
| Reserved | $0.18 /GPU/hr from $0.06 (6 mo) | No reserved listings | |
| Spot | -- /GPU/hr from $0.06 | No spot listings |
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 spot on the A4000: 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
A4000 vs H800 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | A4000 | H800 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 16 GB GDDR6 | 80 GB HBM2e | 5x more on H800 |
| Bandwidth | 448 GB/s | 2,000 GB/s | 4.5x higher on H800 |
| Bus width | 256-bit | 5,120-bit | 20x wider on H800 |
| Compute · dense | |||
| FP8 | Not supported | 1,513 TFLOPS | H800 only |
| FP16 / BF16 | 76.7 TFLOPS | 756.5 TFLOPS | 9.9x higher on H800 |
| INT8 | 1,513 TOPS | ||
| FP32 | 19.2 TFLOPS | 51 TFLOPS | 2.7x higher on H800 |
| Platform | |||
| Interconnect | PCIe only | NVLink 400 GB/s | NVLink on H800 only |
| Board power | 140 W | 350 W | 2.5x higher on H800 |
| Released | Q2 2021 | Q1 2023 | 2 years newer on H800 |
| Precision | |||
| Supported formats | FP16BF16TF32FP32INT4INT8 | FP8FP16BF16TF32FP32FP64INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: A4000 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 | A4000 | H800 |
|---|---|---|
Vast.ai
USA
|
$0.07 /GPU/hr On-demand | -- |
GPU.ai
UAE
|
$0.09 /GPU/hr On-demand | -- |
Hyperstack
UK
|
$0.15 /GPU/hr On-demand | -- |
Spheron
Singapore
|
$0.16 /GPU/hr On-demand PCIe | -- |
Sesterce
France
|
$0.17 /GPU/hr On-demand | -- |
Runpod
USA
|
$0.17 /GPU/hr On-demand | -- |
Runcrate
USA
|
$0.20 /GPU/hr On-demand PCIe | -- |
EmpirioLabs AI
USA
|
$0.25 /GPU/hr On-demand | -- |
13 providers list the A4000 and 0 the H800. Every listing is on the A4000 page and the H800 page.
Similar GPUs
Other comparisons in the same class.
-
Nvidia T4
16 GB GDDR6 · 33% less bandwidth than the A4000
From $0.10 /GPU/hr Compare -
Nvidia RTX 4000 Ada
20 GB GDDR6 · 20% less bandwidth than the A4000
From $0.20 /GPU/hr Compare
-
Nvidia A5000
24 GB GDDR6 · 71% more bandwidth than the A4000
From $0.23 /GPU/hr Compare
-
Nvidia H100
80 GB HBM3 · 68% more bandwidth than the H800
From $1.30 /GPU/hr Compare
-
Nvidia H200
141 GB HBM3e · 2.4x the bandwidth of the H800
From $2.09 /GPU/hr Compare
Our data for Nvidia A4000 was last updated on Sept. 14, 2026, and for Nvidia H800 on Sept. 14, 2026.