{"slug": "offgrid-ai-i-now-run-3-8-27b-q8-offgrid", "title": "OFFGRID AI, I now run 3.8 27b Q8 offgrid :)", "summary": "A forum user reports running an off-grid AI setup with a 3.8 27b Q8 model across five GPUs (1x5060/8GB, 2x3060/12GB, 1x1660s/6GB, 1x1070/8GB) at 550W, powered by a Renogy 2000W inverter, two 220Ah 24V LiTime batteries, and 1400W solar panels (1100W actual), achieving 200-second responses for hard questions. The setup also runs seven Proxmox VMs, six websites, RAG/EMBED, Grafana, and a TrueNAS server with 10 spinners and 4 SSDs.", "body_md": "my prior post in “new commers” shows my setup ([ai](https://forum.level1techs.com/tag/ai) & gaming $4 84gb vram) , but i am running Q8 only on these shards atm. 1x5060/8gb, 2x 3060/12gb, 1x1660s/6gb, 1x1070/8gb with 200sec response for hard questions (according to opus5 max). 550w usage. i have a renogy 2000w inverter, 2x 220ah 24v litime batts, 1400w solar panels (1100w actual). i also run 7 proxmox VM’s…6 websites, RAG/EMBED, grafana, other small programs and a trunas server (10 spinners and 4 ssd’s) spinners are idle most of the time atm due to not using jellyfin to much hence the 550w.", "url": "https://wpnews.pro/news/offgrid-ai-i-now-run-3-8-27b-q8-offgrid", "canonical_source": "https://forum.level1techs.com/t/offgrid-ai-i-now-run-3-8-27b-q8-offgrid/254777#post_1", "published_at": "2026-09-02 02:03:30+00:00", "updated_at": "2026-09-02 02:21:49.453269+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-infrastructure", "ai-tools"], "entities": ["Renogy", "LiTime", "Proxmox", "TrueNAS", "Grafana", "NVIDIA GeForce RTX 5060", "NVIDIA GeForce RTX 3060", "NVIDIA GeForce GTX 1660 Super"], "alternates": {"html": "https://wpnews.pro/news/offgrid-ai-i-now-run-3-8-27b-q8-offgrid", "markdown": "https://wpnews.pro/news/offgrid-ai-i-now-run-3-8-27b-q8-offgrid.md", "text": "https://wpnews.pro/news/offgrid-ai-i-now-run-3-8-27b-q8-offgrid.txt", "jsonld": "https://wpnews.pro/news/offgrid-ai-i-now-run-3-8-27b-q8-offgrid.jsonld"}}