Ollama hosting

Ollama wraps llama.cpp with a one-line install, a model registry, and an OpenAI-compatible API. It runs GGUF quantized models efficiently on a single GPU (or CPU), making it ideal for development, internal tools, and low-traffic apps. It is not built for high-concurrency production serving. That's vLLM/SGLang territory.

Providers with a ready-made Ollama path

ProviderHow
RunPod Ollama template in the gallery; expose port 11434 Deploy
Vast.ai Ollama template in recommended templates Deploy
Novita AI Ollama template in the template marketplace Deploy

Everywhere else: `curl -fsSL https://ollama.com/install.sh | sh && ollama run llama3.3` on any GPU VM.

Which GPU to rent

GGUF Q4 quants need roughly 0.6 GB VRAM per billion params. A 24 GB card (RTX 4090) comfortably runs 32B-class models at Q4.

Live floors refreshed 2026-08-23
Model classGPUVRAMFrom $/hrCheapest at
Up to ~17B (FP8) / ~34B (INT4) RTX 4090 24 GB $0.134marketplace Vast.ai Rent
Up to ~23B (FP8) / ~46B (INT4) RTX 5090 32 GB $0.321marketplace Vast.ai Rent
Up to ~34B (FP8) / ~69B (INT4) L40S 48 GB $0.467marketplace Vast.ai Rent
Up to ~58B (FP8) / ~116B (INT4) H100 SXM 80 GB $1.34marketplace Vast.ai Rent
Up to ~102B (FP8) / ~205B (INT4) H200 141 GB $2.00spot Verda
Up to ~130B (FP8) / ~261B (INT4) — MoE giants go multi-GPU B200 180 GB $3.06spot Verda

Rent vs API: when self-hosting Ollama pays off

Self-hosting wins when utilization is high and steady. A rented GPU bills every hour whether you use it or not, while APIs bill per token. Run your numbers in the breakeven calculator, or check any open model's page (e.g. Llama 3.3 70B) for a side-by-side estimate.

Other stacks