Cloudoora GPU Cloud Instance - RTX & Workstation
Rent Cloudoora GPU instances with 6 to 48 GB of VRAM, from RTX A2000 to L40S, and run any open model yourself.
Overview
Cloudoora's GPU cloud instances give you a single NVIDIA consumer, workstation or L40-class GPU with 6 to 48 GB of VRAM, and you install and serve the model yourself. They suit small and mid-size open-weight models, up to 70B-class models quantized on the 48 GB cards. Prices run from about US$105 to US$1,022 a month, and most GPUs can also be billed by the hour (US$0.14 to US$1.31) with a one-hour minimum. Longer terms of 3 to 36 months are available, with no setup fee.
Specifications
| Hosting type | GPU cloud |
|---|---|
| Model families | Gemma, Llama, Mistral, Qwen, gpt-oss |
| LLM models | Gemma 3 4B, Gemma 3 12B, Gemma 3 27B, Gemma 2 9B, Gemma 2 27B, Llama 3.1 8B Instruct, Llama 3.3 70B Instruct, Mistral NeMo, Mistral Small 3.1, Codestral 22B, Qwen3 30B-A3B, Qwen3 32B, Qwen2.5-Coder 32B Instruct, Qwen2.5 72B Instruct, gpt-oss-20b |
| Pricing range | US$0.14 – US$1.31 |
| Pricing model | Per GPU-hour, Monthly subscription |
| Free tier available | No |
| Data center locations | Finland, France, Germany, Sweden, United Arab Emirates, United Kingdom, United States |
| Hardware / GPU options | Single-GPU instances: RTX A2000 (6 GB), RTX 3070 (8 GB), RTX 3080 (10 GB), RTX 3080 Ti and 4070 Ti (12 GB), RTX A4000, Tesla V100, V100 SXM2, RTX 4080 SUPER, RTX 5080 and RTX 2000 Ada (16 GB), RTX 4000 Ada SFF and RTX A4500 (20 GB), RTX A5000, RTX 3090, RTX 3090 Ti, RTX 4090, RTX PRO 4000 and PRO 6000 MIG 24GB (24 GB), RTX PRO 4500, RTX 5000 Ada and RTX 5090 (32 GB), and RTX A6000, A40, RTX 6000 Ada, L40, L40S, RTX PRO 5000 and PRO 6000 MIG 48GB (48 GB). |
| VRAM & memory | 6 GB – 48 GB |
| Maximum model size | 72B |
| OpenAI-compatible API | No |
News about Cloudoora
All news →Cloudoora: GPU cloud instances now in our directory
We've added Cloudoora, the Helsinki-based hosting company, with two GPU cloud plans for running open models yourself, from an RTX A2000 up to an NVIDIA B300.
