Overview
Nvidia RTX 3090
|
Nvidia RTX 4070 Ti Super
|
|
|---|---|---|
| Summary | Popular legacy consumer GPU for local AI development with NVLink. | Mid-range Ada Lovelace GPU for local inference and content creation. |
| Architecture | Ampere | Ada Lovelace |
| Memory | 24GB GDDR6X | 16GB GDDR6X |
| Memory Bandwidth | 936 GB/s | 672 GB/s |
| Performance | 284 TFLOPS (FP16) | 388 TFLOPS (FP16) |
| Release Date | Q3 2020 | Q1 2024 |
| Performance Segment | Mid-Range | Mid-Range |
| Datasheet | Link | Link |
Price comparison
How we rank providers
Default ranking
Each provider appears once per GPU, ranked on three things in order:
- Availability: in stock, then waitlist, then unconfirmed, then out of stock. A price you can act on outranks a cheaper one you cannot.
- Billing type: on-demand rates rank ahead of spot and reserved ones. A spot rate is cheaper because it can be reclaimed, and a reserved rate because it is a commitment.
- Price: the lowest hourly price a provider charges for a single one of that GPU, with other currencies converted to USD first.
Providers that tie on price are sorted alphabetically.
Reserved rates are not separated by term length, so a multi-year commitment can rank above a one-month one. The term is shown beneath each price.
Transparency and funding
Ads and sponsors: Any paid placements are fixed at the top and labeled as sponsored content.
Affiliates: Any affiliate links will be indicated to you as well. We may earn a commission if you click them, but this never influences the ranking order.
RTX 3090 Pricing
You can start using a RTX 3090 for $0.10/hr per GPU (on-demand). It's a low-risk price point for smaller workloads compared to the market high of $0.50/hr. Spot instances start lower, at $0.07/hr per GPU.
Vast.ai
Our sponsor
13 configs · 1x-8x
$0.11
On-Demand
HyperAI
In stock
8 configs · 1x-8x
$0.10
On-Demand
GPU.ai
In stock
5 configs · 1x-8x
$0.11
On-Demand
Theta EdgeCloud
In stock
1 config · 1x
$0.12
On-Demand
Runpod
In stock
6 configs · 1x-8x
$0.22
On-Demand
Salad
1 config · 1x
$0.12
On-Demand
SwissGPU
1 config · 1x
$0.31
On-Demand
TensorDock
1 config · 1x
$0.31
On-Demand
Vast.ai
Our sponsor
5 configs · 1x-8x
$0.11
On-Demand
HyperAI
In stock
4 configs · 1x-8x
$0.10
On-Demand
GPU.ai
In stock
5 configs · 1x-8x
$0.11
On-Demand
Theta EdgeCloud
In stock
1 config · 1x
$0.12
On-Demand
Runpod
In stock
5 configs · 1x-4x
$0.22
On-Demand
Salad
1 config · 1x
$0.12
On-Demand
SwissGPU
1 config · 1x
$0.31
On-Demand
TensorDock
1 config · 1x
$0.31
On-Demand
RTX 4070 Ti Super Pricing
For smaller projects, the RTX 4070 Ti Super is available around $0.11/hr per GPU (on-demand). This tier offers a 52% discount compared to the higher end of the market ($0.23/hr). Spot instances start lower, at $0.07/hr per GPU.
Heads up: We do our best to keep these specs & prices accurate. However, cloud costs may fluctuate based on region, usage, and other factors not listed here. These are estimates based on common setups and are for informational purposes only. Always verify current rates & exact specs with the provider before provisioning.
Alternative GPUs
Here's how these GPUs compare against alternatives:
Nvidia RTX 3090
vs
Nvidia RTX 4090
Nvidia RTX 3090
vs
Nvidia RTX 3090 Ti
Nvidia RTX 4070 Ti Super
vs
Nvidia RTX 4080
Nvidia RTX 4070 Ti Super
vs
Nvidia RTX 4070 Ti
Our data for Nvidia RTX 3090 was last updated on Aug. 20, 2026, and for Nvidia RTX 4070 Ti Super on Aug. 20, 2026.