Two Nvidia consumer GPUs, one Ampere and one Ada Lovelace: 24 GB GDDR6X against 8 GB GDDR6, 3.4x the memory bandwidth on the RTX 3090, and NVLink 112 GB/s on the RTX 3090 where the RTX 4060 is PCIe only.
At a glance
Memory
- RTX 3090
- 24 GB
- RTX 4060
- 8 GB
3x more on RTX 3090
Memory bandwidth
- RTX 3090
- 936 GB/s
- RTX 4060
- 272 GB/s
3.4x higher on RTX 3090
Cheapest on-demand
- RTX 3090
- $0.10 /GPU/hr
- RTX 4060
- $0.06 /GPU/hr
43% cheaper on RTX 4060
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | RTX 3090 | RTX 4060 | Difference |
|---|---|---|---|
| On-demand | $0.20 /GPU/hr from $0.10 | $0.08 /GPU/hr from $0.06 | 2.4x more expensive on RTX 3090 |
| Reserved | -- /GPU/hr from $0.06 (1 mo) | -- /GPU/hr from $0.07 (1 mo) | |
| Spot | $0.11 /GPU/hr from $0.07 | -- /GPU/hr from $0.04 |
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 reserved and spot on the RTX 4060: 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 4060 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | RTX 3090 | RTX 4060 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 24 GB GDDR6X | 8 GB GDDR6 | 3x more on RTX 3090 |
| Bandwidth | 936 GB/s | 272 GB/s | 3.4x higher on RTX 3090 |
| Bus width | 384-bit | 128-bit | 3x wider on RTX 3090 |
| Compute · dense | |||
| FP8 | Not supported | 60.5 TFLOPS | RTX 4060 only |
| FP16 / BF16 | 71.2 TFLOPS | 30.2 TFLOPS | 2.4x higher on RTX 3090 |
| INT8 | 284.7 TOPS | 120.9 TOPS | 2.4x higher on RTX 3090 |
| FP32 | 35.6 TFLOPS | 15.1 TFLOPS | 2.4x higher on RTX 3090 |
| Platform | |||
| Interconnect | NVLink 112 GB/s | PCIe only | NVLink on RTX 3090 only |
| Board power | 350 W | 115 W | 3x higher on RTX 3090 |
| Released | Q3 2020 | Q2 2023 | 3 years newer on RTX 4060 |
| Precision | |||
| Supported formats | FP16BF16TF32FP32INT4INT8 | FP8FP16BF16TF32FP32INT4INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: RTX 3090 datasheet and RTX 4060 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 4060 /GPU/hr |
|---|---|---|
Vast.ai
|
On-Demand $0.11 | On-Demand $0.06 |
Salad
|
On-Demand $0.17 | On-Demand $0.08 |
Theta EdgeCloud
|
On-Demand $0.13 | On-Demand $0.12 |
HyperAI
|
On-Demand $0.10 | -- |
GPU.ai
|
On-Demand $0.16 | -- |
Lium
|
On-Demand $0.16 | -- |
Runpod
|
On-Demand $0.22 | -- |
EmpirioLabs AI
|
On-Demand $0.80 | -- |
Database Mart
|
-- | Reserved (24mo) $0.21 |
10 providers list the RTX 3090 and 4 the RTX 4060. Every listing is on the RTX 3090 page and the RTX 4060 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 $0.18 /GPU/hr Compare -
Nvidia RTX 3060
From $0.04 /GPU/hr Compare -
Nvidia RTX 4060 Ti
From $0.08 /GPU/hr Compare
Our data for Nvidia RTX 3090 was last updated on Sept. 7, 2026, and for Nvidia RTX 4060 on Sept. 7, 2026.