GPU rental guides

Practical articles: picking a GPU, how much memory models need, running Stable Diffusion, ComfyUI, Ollama and vLLM on a rented server, and not overpaying.

How much VRAM an LLM needs: a table and a rule of thumbHow to estimate memory for model weights at fp16, int8 and int4, how much 8B, 14B, 32B and 70B models need, and why context also uses memory.6 min read
Ollama and vLLM on a rented GPU: chat and API in 10 minutesStep by step: a model in Ollama with chat and API, and vLLM with an OpenAI-compatible server on a rented GPU. Commands, checks and common mistakes.7 min read
Stable Diffusion and FLUX on a rented GPU: what to choose and how to startWhich card to pick for SD 1.5, SDXL and FLUX, how to start Forge or ComfyUI on a rented server, and how to keep costs under control.6 min read
ComfyUI on your own server: setup, models and workflowsHow to work with ComfyUI on a rented GPU server: the model folder layout, the node manager, saving workflows and reaching the interface.6 min read
How not to overpay for GPU rental: stopping, disk and trafficWhat is actually billed when renting a GPU per minute: the GPU, the disk while stopped, and traffic. How to stop or delete a server so you do not pay for idle time.5 min read
What interruptible GPU servers are and when to use themAn interruptible server costs less than on-demand, but it can be paused if someone outbids you. Which tasks suit it and how to avoid losing work.4 min read
Which GPU to pick for LoRA training: SDXL, FLUX and 7B modelsChoosing a card for LoRA training on SDXL, FLUX and 7B LLMs: memory requirements, QLoRA versus LoRA, and how to estimate training time before you start.5 min read
Connecting to a GPU server over SSH: keys, first login and filesHow to create an SSH key, add it to your account, connect to a rented GPU server and transfer files. Commands for Linux, macOS and Windows.5 min read
How to train AI models without your own GPUHow to rent a GPU for training and fine-tuning models: how much memory you need, which card to pick, step by step, and how to pay per minute.7 min read
Renting a GPU for AI from RussiaHow to choose a GPU rental service for AI from Russia: per-minute billing in rubles, ready templates, payment options and the first launch.6 min read