GPU rental · Starter tier
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–8B model, embeddings or experiments, or both cards for two independent streams — by the hour, with full SSH access, switched on and off in the console.
Why AxForge
| Real capacity at the starter price | 12 GB GDDR6 per card runs 7B–8B models quantized, embeddings and dev/test work. Take one card, or both for two independent streams. |
|---|---|
| Community decode: 75.6 t/s on one card | On the same-workload llama.cpp CUDA scoreboard (Llama 2 7B Q4_0) the RTX 3060 decodes at 75.6 t/s with 2,138 t/s prompt processing. Community measurements, not ours. |
| Stockholm, by the hour | A dedicated machine in Sweden (eu-se-1): pay per started hour and switch it on and off in the console, or book a week, month or year for a lower rate. |
Specifications
| Configurations | One RTX 3060 (12 GB) · or the dual-GPU machine (two cards, 24 GB in total) |
|---|---|
| Memory | 12 GB GDDR6 per card |
| Availability | Bookable in the console — take the next free slot or reserve a start time |
| Tenancy | Dedicated, your traffic only, full SSH access |
| Price, one card | €0.20 /hour on demand |
| Price, both cards | €0.34 /hour on demand |
| Longer bookings | from €0.16/hour by the year for one card |
| Region | Stockholm, Sweden (eu-se-1) |
| Community decode | 75.6 t/s on one card (llama.cpp CUDA scoreboard, Llama 2 7B Q4_0) — labelled, not ours |
Full details, benchmarks and FAQ on the RTX 3060 page. Prices exclude VAT.
How it works
| 1 | Sign in to AxForge. |
|---|---|
| 2 | Choose RTX 3060 — one card or the dual-GPU machine — and the term: on demand, week, month or year. |
| 3 | Pay in the console; the machine is prepared for you. |
| 4 | Add your SSH key and connect when the machine is yours. |
| 5 | End the rental when your workload is complete. |
Check availability or sign in to start.
FAQ
Yes — it is the starter tier. Check availability in the console and take the next free slot, or reserve a start time.
Both. Rent a single RTX 3060 (12 GB) for a 7B–8B model, embeddings or experiments, or the whole dual-GPU machine (24 GB in total) for two independent streams.
Listed per hour, excl. VAT: one card or both cards on demand; a week, month or year earns a lower rate. The prices are on this page and in the console.
In Stockholm, Sweden (eu-se-1), where AxForge serverless inference also runs.
No. Your model, your traffic, our hardware — prompts never persisted. Only operational metadata is kept for billing and operations.