Self-Hosting · AI Infrastructure

Your Computer as Your Own AI Server

Projects like SoloHost pitch a simple idea: run the model at home, control it from your phone, and let no prompt leave your house. Here's the honest engineering trade-off.

Where does your prompt actually go?

0prompts leaving your network / day
~0 msnetwork latency added
$0.35/daymarginal cost (power or API)
7–70Bpractical model size

Green orbs are your prompts. In local mode they orbit your house; in cloud mode they stream across the internet to a data center — faster models, but every token transits third-party hardware. Drag to rotate.

The real trade-off table

FactorLocal (e.g. 8–70B open model)Cloud API (frontier model)
PrivacyPrompts never leave your LANProvider ToS + retention policies apply
QualityGood for drafting, summaries, RAG over your filesState of the art reasoning & coding
Up-front cost$600–$2,500 (used RTX 3090/4090 or Mac w/ 32–64GB unified memory)$0
Marginal costElectricity: ~0.35 kW × $0.15/kWh ≈ $0.05/hr under loadRoughly $0.15–$15 per million tokens depending on model
Speed15–60 tokens/sec typical on consumer GPUs50–200+ tokens/sec, plus 50–300 ms network RTT
Uptime & opsYours to maintain (updates, cooling, remote access)Provider's problem

Worked example: the break-even

Say you burn 1M tokens/day on mid-tier cloud models at a blended ~$1.50 per million tokens: $45/month. A used RTX 3090 rig costs ~$1,100 and about $11/month in power at 2 hrs/day load. Break-even: $1,100 ÷ ($45 − $11) ≈ 32 months — and you got a lower-quality model. The honest conclusion: self-hosting rarely wins on pure cost. It wins on privacy (medical notes, client data, contracts), on unlimited experimentation without a meter running, and on offline resilience. That's why the sensible pattern is hybrid: local model for sensitive/bulk work, cloud API when you need frontier reasoning.

If you want to try it this weekend

1) Install Ollama or LM Studio. 2) Pull an 8B open-weight model (Llama or Qwen class) — it runs on 16 GB RAM. 3) Point any OpenAI-compatible client at http://localhost:11434. 4) For phone control, add Tailscale so your devices share a private network — the same "control from anywhere, data stays home" trick the SoloHost pitch describes, no special browser required.

Enjoy this tool? Build your own with Super