---
id: FI-WP-0003
type: workplan
title: "Seed open-weight reserve from baseline recommendations"
domain: agents
repo: freedom-intelligence
status: finished
owner: grok
topic_slug: freedom-intelligence
priority: medium
created: "2026-07-24"
updated: "2026-07-28"
depends_on:
  - FI-WP-0001
state_hub_workstream_id: "7513a853-24bf-4826-9ed9-3e8ed8ab0fa5"
---

# FI-WP-0003 — Seed open-weight reserve from baseline recommendations

## Goal

Turn baseline + **strategic reserve policy** into a **real, policy-compliant reserve**:
approve high-priority catalog candidates, download to the **pinned bulk store**,
verify checksums, and leave lower-priority items as candidates for later briefs.

**Storage pin:** `D:\vault\coulomb\freedom-intelligence\` /
`/mnt/d/vault/coulomb/freedom-intelligence/`

Soft quota **850 GiB**. Tool: `scripts/collect_model.py` (weights-only, MANIFEST).

## Tasks

### T01 — Seed catalog YAML

```task
id: FI-WP-0003-T01
status: done
priority: high
state_hub_task_id: "5d2a493b-a189-4eae-8a40-18ce8e0ab17d"
```

### T02 — Operator approve R spine + S priority order

```task
id: FI-WP-0003-T02
status: done
priority: high
state_hub_task_id: "909263c7-7148-45fa-98bc-5d2bafacf507"
```

**2026-07-28 approvals** (`approved_by: bernd`):

| Tier | Models |
| ---- | ------ |
| R | Qwen3-8B, Llama-3.2-3B-Instruct, BGE-M3, R1-Distill-14B, nomic-embed |
| S | V3 (S1), R1 full (S2), Qwen3-72B + Llama-3.3-70B (S4) — **collect deferred** |

### T03 — Download R + strategic S + verify

```task
id: FI-WP-0003-T03
status: done
priority: high
state_hub_task_id: "222969d0-f3af-46fb-a303-f76800c80ff9"
```

**Verified on VAULT (weights + MANIFEST sha256):**

- nomic-embed-text-v1.5 (~0.5 GiB)
- BGE-M3 (~2.1 GiB)
- Qwen3-8B (~15.3 GiB)
- R1-Distill-Qwen-14B (~27.5 GiB)

**Residual:**

- Llama-3.2-3B-Instruct — deferred (HF gate; need `HF_TOKEN` + Meta license)
- S giants — deferred per out-of-scope / capacity (prefer official compressed later)

### T04 — W-tier and remaining S decision pass

```task
id: FI-WP-0003-T04
status: done
priority: medium
state_hub_task_id: "33daa2cf-f9fd-430d-a4e4-58996c900ca6"
```

W remain **candidate**: Qwen3-14B, R1-Distill-32B, bge-reranker-v2-m3.  
S approved with **collection_deferred** history events.

### T05 — Reserve index snapshot

```task
id: FI-WP-0003-T05
status: done
priority: low
state_hub_task_id: "9974b98a-e1b3-4b7a-b2c2-0fd2cba65f97"
```

`inventory/RESERVE-STATUS.md` written.

## Acceptance (workplan-level)

- [x] Catalog seeded + profile/SWOT
- [x] Storage pin complete
- [x] R + S approved (S deferred on disk)
- [x] R spine verified on media (embeds + Qwen3-8B + R1-Distill-14B; Llama gated residual)
- [x] RESERVE-STATUS snapshot

## Residual handoffs

| Residual | Action |
| -------- | ------ |
| Llama-3.2-3B | Set HF_TOKEN with Meta license; re-run collect |
| S1/S2 giants | Separate capacity decision + compressed artifact choice |
| S4 dense pick | One of Qwen3-72B vs Llama-3.3-70B under quota |

## Out of scope

- Hosting inference endpoints
- Full DeepSeek-V3/R1 671B pull without separate capacity decision
- Dataset reserve