mirror of
https://github.com/kuhyx/testsAndMisc.git
synced 2026-11-10 22:27:01 +01:00
setup_local_llm.sh: idempotent Bash installer for a self-hosted local LLM stack tuned for the RTX 3090 (24GB) — installs ollama-cuda, writes a systemd drop-in enabling flash attention + Q8_0 KV-cache quantisation, pulls the model, creates a custom Ollama model with a developer system prompt, and launches Open WebUI via Docker. Verification: bash -n and shellcheck -x clean (see evidence artifact). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_017RRCdR4D8SaVrN2xraMQxM |
||
|---|---|---|
| .. | ||
| control_from_mobile.sh | ||
| install_unreal_mcp_kvick.sh | ||
| install_unreal_mcp.sh | ||
| migrate_github_to_gitea.sh | ||
| raspberry_pi_flash_sd.sh | ||
| raspberry_pi_nextcloud.sh | ||
| setup_activitywatch.sh | ||
| setup_dns_blocker.sh | ||
| setup_dwm.sh | ||
| setup_gitea.sh | ||
| setup_local_llm.sh | ||
| setup_nextcloud_raspberry.sh | ||
| setup_wireguard_ssh.sh | ||