fizzlepoof/truenas-stacks
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

chore: sync homelab ops, identity, and monitoring docs

Browse Source
This commit is contained in:
Fizzlepoof
2026-05-21 02:01:09 +00:00
parent 4c41b19e13
commit 2e99873634
44 changed files with 6295 additions and 346 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
docs/servers/PLAUSIBLEDENABILITY.md
View File

@@ -31,18 +31,24 @@ Primary Docker host running all production workloads.
RTX 2080 Ti used by:
- Plex (hardware transcoding)
- immich-ml (CUDA face recognition)
- Ollama light-tier inference (qwen2.5:14b and smaller)
- Ollama light-tier inference for the main AI stack and local Honcho backend
> **Note:** Whisper moved to N.O.M.A.D. (10.5.1.16:8786) as CPU inference — avoids VRAM conflict with Ollama. See [NOMAD.md](NOMAD.md).
Recommended models for 11GB VRAM:
| Model | VRAM | Best for |
|-------|------|---------|
| `qwen2.5:14b` | ~8GB | General use, coding, reasoning |
| `qwen2.5:7b` | ~5GB | Cheap/default reasoning, summaries, derivation |
| `qwen2.5:14b` | ~8GB | Heavier reasoning / high-max paths |
| `qwen2.5-coder:7b` | ~5GB | Code tasks |
| `deepseek-r1:8b` | ~5GB | Math, logic |
| `phi4` | ~8GB | Analytical tasks |
Current light-tier notes:
- PD Ollama is the active light-tier endpoint for LiteLLM on `http://10.5.1.6:11434`
- Local Honcho currently points at PD Ollama over LAN (`http://10.5.1.6:11434/v1`) instead of using a separate local model host
- Current Honcho routing split keeps embeddings on `nomic-embed-text:latest`, cheap/default paths on `qwen2.5:7b`, and deeper high/max paths on `qwen2.5:14b`
## Remote Access
- Pangolin VPS + Newt for external services
- SSH from Windows 11