# Model tags used by this kit

| Tag | Base | Digest (tag) | Params | Quant | Status |
|---|---|---|---|---|---|
| `botshelf-deep-research-3b` | `llama3.2:latest` | `5b78ca059dc3…c03e84` | 3.2B | Q4_K_M | create from Modelfile |
| `botshelf-doc-review` | `llama3.2:1b` | `3533ded51d41…d9be64` | 1.2B | Q8_0 | create from Modelfile |

Full digests: `MODEL-TAGS.json`.

## Create (if tags missing)

```bash
ollama pull llama3.2
ollama pull llama3.2:1b
ollama create botshelf-deep-research-3b -f models/Modelfile.botshelf-deep-research-3b
ollama create botshelf-doc-review -f models/Modelfile.botshelf-doc-review
ollama show botshelf-deep-research-3b
ollama show botshelf-doc-review
```

If `ollama` is unavailable on your machine, mark both tags **UNAVAILABLE** and use the **manual handoff** path in the kit README (copy/paste into any two chat UIs). Do not invent cloud-provider outputs.

## Honesty

- Sequential local Ollama-tag workflow ≠ automatic simultaneous multi-cloud.
- Two tags on one Ollama host are two model identities only when digests/parameter sizes differ (they do here).