# Open-weight reserve status

**As of:** 2026-07-28  
**Store:** `/mnt/d/vault/coulomb/freedom-intelligence/` (`D:\vault\coulomb\freedom-intelligence\`)  
**Soft quota:** 850 GiB · **Hard stop:** 920 GiB  

---

## Portfolio snapshot

| Class | Count | Status mix |
| ----- | ----: | ---------- |
| Catalog entries | 12 | see table |
| **verified** on disk | 4 | R embeds + Qwen3-8B + R1-Distill-14B |
| **approved** (pull deferred) | S giants + Llama edge | capacity / HF gate |
| **candidate** (W) | 3 | headroom-gated |

### Disk use (model tree)

Run: `du -sh /mnt/d/vault/coulomb/freedom-intelligence/models`

| Path | Role | Approx |
| ---- | ---- | ------ |
| `models/nomic-ai__nomic-embed-text-v1.5/main` | R embed | ~0.5 GiB verified |
| `models/BAAI__bge-m3/main` | R embed | ~2.1 GiB verified |
| `models/Qwen__Qwen3-8B/main` | R instruct | ~15.3 GiB verified |
| `models/deepseek-ai__DeepSeek-R1-Distill-Qwen-14B/main` | R reason | ~27.5 GiB verified |

**~45 GiB** of soft 850 GiB used by verified R spine → **~800+ GiB** headroom for S.

---

## Decision matrix (2026-07-28)

| Id | Tier | Decision | Disk |
| -- | ---- | -------- | ---- |
| Qwen3-8B | R | **verified** | yes |
| Llama-3.2-3B-Instruct | R | **approved** | deferred — HF gate (need token) |
| BGE-M3 | R | **verified** | yes |
| R1-Distill-Qwen-14B | R | **verified** | yes |
| nomic-embed-text-v1.5 | R | **verified** | yes |
| DeepSeek-V3 | S1 | **approved**, **collection deferred** | no — capacity / compressed plan later |
| DeepSeek-R1 full | S2 | **approved**, **collection deferred** | no — distill covers runnable reason |
| Qwen3-72B | S4 | **approved**, **collection deferred** | no — after R; pick vs Llama-70B |
| Llama-3.3-70B-Instruct | S4 | **approved**, **collection deferred** | no — gated + vs Qwen-72B |
| Qwen3-14B | W | **remain candidate** | no |
| R1-Distill-32B | W | **remain candidate** | no |
| bge-reranker-v2-m3 | W | **remain candidate** | no |

---

## Hardware coverage gaps

| Need | Status |
| ---- | ------ |
| Default local instruct (8B) | **Covered** (Qwen3-8B) |
| Edge micro-agent | Llama-3.2-3B blocked on HF auth |
| Multilingual RAG embed | **Covered** (BGE-M3 + nomic) |
| Local reason | **Covered** (R1-Distill-14B) |
| Frontier-open general MoE offline | Deferred S1 (V3 class) |
| Full open reasoner MoE | Deferred S2 |

---

## Next pulls (operator)

1. Set `HF_TOKEN` and pull Llama-3.2-3B-Instruct.  
2. Reassess soft quota; pick **one** of Qwen3-72B vs Llama-3.3-70B before any S1 giant.  
3. For S1/S2: prefer **official compressed** distributions under soft quota.

Tool: `scripts/collect_model.py` (weights-only, sequential, writes `MANIFEST.json`).