← All hosting plans

xCloud Ollama Hosting

Run Ollama on a managed xCloud Cloud VPS with 16 or 24 GB of RAM and pull open models up to about 27B yourself.

Specifications

Plan information
Hosting typeGPU cloud
Model familiesLlama, Gemma, Qwen, Mistral, Phi, DeepSeek, gpt-oss
LLM modelsLlama 3.2 1B Instruct, Llama 3.2 3B Instruct, Llama 3.1 8B Instruct, Gemma 3 1B, Gemma 3 4B, Gemma 3 12B, Gemma 3 27B, Gemma 2 9B, Gemma 2 27B, Qwen3 0.6B, Qwen3 1.7B, Qwen3 4B, Qwen3 8B, Qwen3 14B, Qwen3 30B-A3B, Mistral NeMo, Mistral Small 3.1, Phi-4, DeepSeek-R1-Distill-Qwen-7B, DeepSeek-R1-Distill-Llama-8B, DeepSeek-R1-Distill-Qwen-14B, gpt-oss-20b
Pricing rangeUS$59.99 – US$84.99
Pricing modelMonthly subscription
Free tier availableNo
Data center locationsUnited States, Germany, United Kingdom, Netherlands
Hardware / GPU optionsCPU-only managed Cloud VPS (no GPU): 16 GB RAM, 6 vCPU, 200 GB NVMe (US$59.99/month); 24 GB RAM, 8 vCPU, 300 GB NVMe (US$84.99/month). 30 TB bandwidth on each. Or bring your own server, including GPU machines.
VRAM & memory
Maximum model size27B
OpenAI-compatible APIYes

View plan ↗

News about xCloud

All news →