RTX 3060 rental from €0.12/h
Renting an NVIDIA GeForce RTX 3060 12GB on VRAMfarm costs from €0.12 an hour. It is a consumer card on the Ampere architecture (2021) with 12 GB of GDDR6 memory: the cheapest card with 12 GB, for learning and tests. You pay by the minute from your balance, with no subscription.
To launch, your balance must cover one hour of the machine. You are billed by the minute for actual use.
What the RTX 3060 is good for
LLM inference
12 GB holds a model of up to about 5B parameters in FP16 and up to 18B in 4-bit, for example 13–14B models such as Qwen 2.5 14B and Phi-4. The memory bandwidth of 360 GB/s sets how fast tokens are generated.
Image generation
Good for SDXL with optimisations and Stable Diffusion 1.5 without limits.
Training and fine-tuning
LoRA fine-tuning of small models, experiments and training compact networks.
Rendering
Blender Cycles, Octane and Redshift: 12.7 TFLOPS FP32 and 12 GB of memory for your scenes.
Rental cost by period
| Period | Cost |
|---|---|
| 1 hour | €0.12 |
| A day (24 hours) | €3 |
| A week | €20 |
| A month (720 hours) | €86 |
Prices updated 12 November 2026. While the page is open we show the price of the cheapest reliable machine available in the catalogue. Prices are in euros. How VAT applies to your account will be shown at checkout.
Similar GPUs
- RTX A4000: 50% more expensive, 4 GB more memory, FP32 ≈ 19.2 vs 12.7 TFLOPS.
- RTX 4060 Ti: 33% more expensive, 4 GB more memory, FP32 ≈ 22.1 vs 12.7 TFLOPS.
- RTX 3080: 42% more expensive, 2 GB less memory, FP32 ≈ 29.8 vs 12.7 TFLOPS.
How to rent the RTX 3060
- Sign up and top up your balance from €10. To launch, your balance must cover at least one hour of the machine.
- In the dashboard, click Rent a GPU, choose what to run (a ready-made app, PyTorch with Jupyter, vLLM or your own Docker image), then the RTX 3060 and a machine.
- The server is usually ready in 2–5 minutes. When you’re done, click Stop and billing stops. If you will need your models and results again, click Save and stop: /workspace is kept for €0.03 per GB per month and comes back on your next server.
Rental questions
How much does RTX 3060 rental cost?
From €0.12 an hour. Billing is per minute, with a minimum charge of 15 minutes per launch. To launch, your balance must cover one hour of the machine; the rest stays on your balance. Prices updated 12 November 2026.
Which AI models can I run on this card?
12 GB holds an LLM of up to about 5B parameters in FP16 or up to 18B in 4-bit, for example 13–14B models such as Qwen 2.5 14B and Phi-4.
How do I access the rented GPU?
The server is usually ready 2–5 minutes after launch. Ready-made apps for images, video and chat open with a button in the dashboard, and for your own code you get SSH and Jupyter. Developers can choose PyTorch with Jupyter, vLLM, an empty ComfyUI or their own Docker image.
How do I pay?
Top up your balance in euros by card or SEPA transfer, from €10. Payments go through a payment provider that we will announce before launch. VAT, where it applies, is shown at checkout.
How does the RTX 3060 compare with similar cards?
RTX A4000: 50% more expensive, 4 GB more memory, FP32 ≈ 19.2 vs 12.7 TFLOPS. RTX 4060 Ti: 33% more expensive, 4 GB more memory, FP32 ≈ 22.1 vs 12.7 TFLOPS. RTX 3080: 42% more expensive, 2 GB less memory, FP32 ≈ 29.8 vs 12.7 TFLOPS.
What happens to my data after I stop?
The server disk is wiped when you stop. If you need your models and results, click Save and stop: we keep /workspace for €0.03 per GB per month, and your next server gets it automatically. Saving does not work yet for custom Docker images.
Launch the RTX 3060
Available machines with an hourly price, billed by the minute from your balance.