GPU rental · starter tier

RTX 3060 rental in Europe: one card or the whole dual-GPU machine

Name: NVIDIA RTX 3060 dedicated rental
Brand: AxForge
Price: 0.24 EUR
Availability: InStock

The AxForge starter tier: NVIDIA RTX 3060 cards with 12 GB GDDR6 each in a dedicated machine in Stockholm. Take one card for a 7B to 8B model, embeddings or experiments, or both cards (24 GB for two jobs side by side or one larger model split across them) by the hour, with full SSH access, switched on and off in the console.

Available One card 12 GB · or both, 24 GB in total €0.24/hour for one card rtx-3060.axforge.ai

Check availability Need 128 GB? DGX Spark (GB10) €0.24/hour for one card · €0.41/hour for both cards, on demand. A week, month or year earns a lower rate: from €0.17/hour by the year for one card.

Specifications

What you get

Configurations	One RTX 3060 (12 GB), or the dual-GPU machine, two cards with 24 GB in total
Memory	12 GB GDDR6 per card
Availability	Available, take the next free slot in the console, or reserve a start time
Tenancy	Dedicated, your traffic only, full SSH access
Price, one card	€0.24/hour on demand
Price, both cards	€0.41/hour on demand
Longer bookings	from €0.17/hour by the year for one card · from €0.29/hour for both
Terms	Per started hour on demand, or a week, month or year at a lower rate
Region	Stockholm, Sweden (eu-se-1)

The pitch: real capacity at the starter price, dedicated to you. If a model needs more than 12 GB per card, look at the DGX Spark with 128 GB of unified memory, or the request-capacity systems: RTX 3090, RTX 5090 and the RTX 6000 Pro.

Community data

What one card does

On the same-workload llama.cpp CUDA scoreboard the RTX 3060 decodes at 75.6 t/s with 2,138 t/s prompt processing, the baseline of the GPU ladder. That is a 7B to 8B model quantized, embeddings, a dev or test node, or an experiment that should not tie up a bigger machine. Both cards together run two jobs side by side, or one model split across them for 24 GB of room. They are still two 12 GB cards joined over PCIe, so a single request does not get twice as fast.

Which models fit one card: language models · image models · embedding models, estimated from each model's own files and config.

Same-workload numbers from the llama.cpp CUDA scoreboard (Llama 2 7B Q4_0, tg128, full GPU offload). Community measurements, not ours.

How it runs

By the hour, from Stockholm

On demand	Pay per started hour you use, and switch the machine on and off in the console
Reserved start	Book a start time and the machine is prepared for you
Week, month, year	Always on, at a lower hourly rate the longer you book
Access	Your SSH key, root on the machine, your software stack
Location	eu-se-1 · Stockholm. GPU rentals and bare metal run on our machines in Stockholm (eu-se-1) or Málaga (eu-es-1); the console shows each machine's city. AxForge serverless inference runs in Stockholm.

Data & privacy

Dedicated, EU-hosted

Like every AxForge machine: your model, your traffic, our hardware. Prompts are never persisted. Only request metadata (token counts, timestamps, status) is kept for billing and operations. Full policy at axforge.ai/privacy.

FAQ

RTX 3060 rental: common questions

Can I rent an RTX 3060 from AxForge?

Yes, it is the AxForge starter tier. Check availability in the console and take the next free slot, or reserve a start time.

One card or two?

Both. Rent a single RTX 3060 with 12 GB for a 7B to 8B model, embeddings or experiments, or the whole dual-GPU machine with 24 GB in total: two jobs side by side, or one larger model split across both cards.

What does RTX 3060 rental cost?

One card €0.24/hour, both cards €0.41/hour on demand. A week, month or year earns a lower rate: from €0.17/hour by the year for one card. Every price is on the pricing page and in the console.

Where is the machine?

In Stockholm, Sweden (eu-se-1), where AxForge serverless inference also runs.

Do you keep prompts on a rented RTX 3060 machine?

No. Your model, your traffic, our hardware. Prompts are never persisted. Only operational metadata is kept for billing and operations. See the privacy policy.