The GH200 has 2x the memory and 4.2x the bandwidth. The RTX 6000 Ada is cheaper right now.
At a glance
Memory
2x more on GH200
- GH200
- 96 GB
- RTX 6000 Ada
- 48 GB
Memory bandwidth
4.2x higher on GH200
- GH200
- 4,000 GB/s
- RTX 6000 Ada
- 960 GB/s
Cheapest on-demand
87% cheaper on RTX 6000 Ada
- GH200
- $3.87 /GPU/hr
- RTX 6000 Ada
- $0.49 /GPU/hr
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | GH200 | RTX 6000 Ada | Difference |
|---|---|---|---|
| On-demand | -- /GPU/hr from $3.87 | $0.96 /GPU/hr from $0.49 | |
| Reserved | No reserved listings | -- /GPU/hr from $0.43 (3 mo) | |
| Spot | Sold out | -- /GPU/hr from $0.27 |
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 GH200 and reserved and spot 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
GH200 vs RTX 6000 Ada price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | GH200 | RTX 6000 Ada | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 96 GB HBM3 | 48 GB GDDR6 | 2x more on GH200 |
| Bandwidth | 4,000 GB/s | 960 GB/s | 4.2x higher on GH200 |
| Bus width | 384-bit | ||
| Compute · dense | |||
| FP8 | 1,979 TFLOPS | 728.5 TFLOPS | 2.7x higher on GH200 |
| FP16 / BF16 | 989.5 TFLOPS | 364.2 TFLOPS | 2.7x higher on GH200 |
| INT8 | 1,979 TOPS | ||
| FP32 | 67 TFLOPS | 91.1 TFLOPS | 36% higher on RTX 6000 Ada |
| FP64 | 34 TFLOPS | Not supported | GH200 only |
| Platform | |||
| Interconnect | NVLink 900 GB/s | PCIe only | NVLink on GH200 only |
| Released | Q2 2023 | Q4 2022 | 6 months newer on GH200 |
| Precision | |||
| Supported formats | FP8FP16BF16TF32FP32FP64INT8 | FP8FP16BF16TF32FP32INT4INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: GH200 datasheet and RTX 6000 Ada datasheet.
Where to rent them
Providers that rent these GPUs, with each one's cheapest rate. Providers that rent both are listed first.
| Provider | GH200 | RTX 6000 Ada |
|---|---|---|
Sesterce
France
|
$2.52 /GPU/hr On-demand | $1.07 /GPU/hr On-demand |
Denvr
Canada
|
$3.87 /GPU/hr On-demand | -- |
CoreWeave
USA
|
$6.50 /GPU/hr On-demand | -- |
Lambda Labs
USA
|
$2.29 /GPU/hr On-demand | -- |
Vultr
USA
|
$1.99 /GPU/hr Spot | -- |
Vast.ai
USA
|
-- | $0.49 /GPU/hr On-demand |
GPU.ai
UAE
|
-- | $0.65 /GPU/hr On-demand |
Lium
Distributed
|
-- | $0.69 /GPU/hr On-demand |
Massed Compute
USA
|
-- | $0.79 /GPU/hr On-demand |
Runcrate
USA
|
-- | $1.26 /GPU/hr On-demand PCIe |
EmpirioLabs AI
USA
|
-- | $1.40 /GPU/hr On-demand |
TensorDock
Distributed
|
-- | $0.86 /GPU/hr On-demand |
5 providers list the GH200 and 14 the RTX 6000 Ada. Every listing is on the GH200 page and the RTX 6000 Ada page.
Similar GPUs
Other comparisons in the same class.
-
Nvidia H100
80 GB HBM3 · 16% less bandwidth than the GH200
From $1.73 /GPU/hr Compare -
Nvidia H200
141 GB HBM3e · 20% more bandwidth than the GH200
From $2.09 /GPU/hr Compare
-
AMD MI300X
192 GB HBM3 · 32% more bandwidth than the GH200
From $2.59 /GPU/hr Compare -
Nvidia L40S
48 GB GDDR6 · data center card
From $0.38 /GPU/hr Compare
-
Nvidia RTX A6000
48 GB GDDR6 · 20% less bandwidth than the RTX 6000 Ada
From $0.40 /GPU/hr Compare
Our data for Nvidia GH200 was last updated on Sept. 14, 2026, and for Nvidia RTX 6000 Ada on Sept. 14, 2026.