A consumer GPU against a workstation card, one Ampere and one Ada Lovelace: 24 GB GDDR6X against 20 GB GDDR6, 3.3x the memory bandwidth on the RTX 3090, and NVLink 112 GB/s on the RTX 3090 where the RTX 4000 SFF Ada is PCIe only.
At a glance
Memory
- RTX 3090
- 24 GB
- RTX 4000 SFF Ada
- 20 GB
1.2x more on RTX 3090
Memory bandwidth
- RTX 3090
- 936 GB/s
- RTX 4000 SFF Ada
- 280 GB/s
3.3x higher on RTX 3090
Cheapest on-demand
- RTX 3090
- $0.10 /GPU/hr
- RTX 4000 SFF Ada
- $0.43 /GPU/hr
4.3x more expensive on RTX 4000 SFF Ada
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | RTX 3090 | RTX 4000 SFF Ada | Difference |
|---|---|---|---|
| On-demand | $0.24 /GPU/hr from $0.10 | -- /GPU/hr from $0.43 | |
| Reserved | -- /GPU/hr from $0.06 (1 mo) | No reserved listings | |
| Spot | $0.13 /GPU/hr from $0.07 | 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 reserved on the RTX 3090 and on-demand on the RTX 4000 SFF 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
RTX 3090 vs RTX 4000 SFF Ada price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | RTX 3090 | RTX 4000 SFF Ada | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 24 GB GDDR6X | 20 GB GDDR6 | 1.2x more on RTX 3090 |
| Bandwidth | 936 GB/s | 280 GB/s | 3.3x higher on RTX 3090 |
| Bus width | 384-bit | 160-bit | 2.4x wider on RTX 3090 |
| Compute · dense | |||
| FP8 | Not supported | 153.4 TFLOPS | RTX 4000 SFF Ada only |
| FP16 / BF16 | 71.2 TFLOPS | 76.7 TFLOPS | 1.1x higher on RTX 4000 SFF Ada |
| INT8 | 284.7 TOPS | ||
| FP32 | 35.6 TFLOPS | 19.2 TFLOPS | 1.9x higher on RTX 3090 |
| Platform | |||
| Interconnect | NVLink 112 GB/s | PCIe only | NVLink on RTX 3090 only |
| Board power | 350 W | 70 W | 5x higher on RTX 3090 |
| Released | Q3 2020 | Q2 2023 | 2 years newer on RTX 4000 SFF Ada |
| Precision | |||
| Supported formats | FP16BF16TF32FP32INT4INT8 | FP8FP16BF16TF32FP32INT4INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: RTX 3090 datasheet and RTX 4000 SFF Ada datasheet.
Where to rent them
Providers listing these GPUs, those with both first, so you can switch without moving clouds.
| Provider | RTX 3090 /GPU/hr | RTX 4000 SFF Ada /GPU/hr |
|---|---|---|
Runpod
|
On-Demand $0.22 | On-Demand $0.18 |
HyperAI
|
On-Demand $0.10 | -- |
Vast.ai
|
On-Demand $0.11 | -- |
Theta EdgeCloud
|
On-Demand $0.13 | -- |
GPU.ai
|
On-Demand $0.16 | -- |
Lium
|
On-Demand $0.16 | -- |
Salad
|
On-Demand $0.17 | -- |
EmpirioLabs AI
|
On-Demand $0.80 | -- |
Koyeb
|
-- | On-Demand $0.50 |
Hetzner
|
-- | On-Demand $0.43 |
10 providers list the RTX 3090 and 3 the RTX 4000 SFF Ada. Every listing is on the RTX 3090 page and the RTX 4000 SFF Ada page.
Similar GPUs
Other comparisons in the same class.
-
Nvidia RTX 5090
From $0.35 /GPU/hr Compare -
Nvidia RTX 4090
From $0.23 /GPU/hr Compare -
Nvidia RTX 3090 Ti
From $0.15 /GPU/hr Compare -
Nvidia RTX 4000 Ada
From $0.17 /GPU/hr Compare
Our data for Nvidia RTX 3090 was last updated on Sept. 14, 2026, and for Nvidia RTX 4000 SFF Ada on Sept. 14, 2026.