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

Sync network redesign repo state and cutover artifacts

Browse Source
This commit is contained in:
Fizzlepoof
2026-05-22 20:16:21 +00:00
parent 4b1e3d4061
commit 9e6dde7695
59 changed files with 5389 additions and 244 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
docs/servers/PLAUSIBLEDENABILITY.md
View File

@@ -33,7 +33,7 @@ RTX 2080 Ti used by:
- immich-ml (CUDA face recognition)
- 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).
> **Note:** Whisper moved to N.O.M.A.D. (10.5.30.7:8786) as CPU inference — avoids VRAM conflict with Ollama. See [NOMAD.md](NOMAD.md).
Recommended models for 11GB VRAM:
| Model | VRAM | Best for |
@@ -45,8 +45,8 @@ Recommended models for 11GB VRAM:
| `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
- PD Ollama is the active light-tier endpoint for LiteLLM on `http://10.5.30.6:11434`
- Local Honcho currently points at PD Ollama over LAN (`http://10.5.30.6:11434/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