freedom-intelligence/research/2026-07-24-nas-strategic-collection-plan.md
tegwick a83ef0a79a Register reserve under agents hub and pin VAULT storage.
Classify freedom-intelligence for State Hub (agents domain), sync FI-WP-0001..0003 with hub IDs, enrich catalog entries with profile/SWOT, and pin the open-weight reserve to D:\vault\coulomb\freedom-intelligence\ with strategic S-tier policy.
2026-07-28 00:25:21 +02:00

94 lines
3.3 KiB
Markdown
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# NAS strategic collection plan (1 TB)
**Date:** 2026-07-24
**Decision:** `docs/decisions/2026-07-24-nas-strategic-reserve.md`
**Soft quota:** 850 GiB on 1 TB local NAS
---
## Intent
Capture the **most capable open-weight models** for long-term optionality, **even
if they cannot run on current lab GPUs**, plus keep a **runnable spine** for
daily local use.
---
## Tier R — runnable spine (keep resident)
| Model | Est. (Q4 / fp16) | Role |
| ----- | ---------------- | ---- |
| Qwen3-8B | ~5 / ~16 GiB | Default instruct + FT |
| Llama-3.2-3B-Instruct | ~2 / ~6 GiB | Edge |
| BGE-M3 | ~2 GiB | Multilingual embed |
| DeepSeek-R1-Distill-Qwen-14B | ~9 / ~28 GiB | Local reason |
| nomic-embed-text-v1.5 | <1 GiB | Light embed |
| **Subtotal (quant-first)** | **~2030 GiB** | |
| **Subtotal (fp16-ish)** | **~5055 GiB** | |
---
## Tier S — strategic capability (best open, may be unrunnable)
Prioritize **one primary artifact per capability niche** so 1 TB is not wasted
on near-duplicates. Prefer official compressed weights when full precision is
hundreds of GiBTB.
| Priority | Capability niche | Representative targets (verify current HF id + license at pull) | Size class (order of magnitude) |
| -------- | ---------------- | ---------------------------------------------------------------- | -------------------------------- |
| **S1** | Best open general / MoE chat | DeepSeek-V3 / V3.2 / V4-class open MoE (latest card) | ~300700+ GiB depending on quant/precision |
| **S2** | Best open reasoner | DeepSeek-R1 full (or successor open reasoner) | similar large |
| **S3** | Best open coding / SWE open weight | Top open code MoE or dense (e.g. GLM-5.x open, Qwen coder large — pick current SOTA open) | tenshundreds GiB |
| **S4** | Strong open dense mid-large | Qwen3-72B or Llama 3.3 70B / Llama 4 open text variant | ~40150 GiB quant / larger fp |
| **S5** | Efficient open frontier family | Gemma 4 large open variants | tens of GiB |
**1 TB portfolio rule of thumb**
```text
R spine (~3055 GiB)
+ S1 one primary giant quant (~300450 GiB) ← first strategic fill
+ optional S4 dense 70B (~4080 GiB Q4)
+ embeds already in R
+ staging headroom
≈ 400600 GiB typical first strategic fill
```
If a single full-precision S1 would exceed soft quota alone, **take the best
official compressed release** of that model and record the base id as the
capability identity.
**Do not** try to store S1 + S2 + S3 all at full precision on this NAS.
---
## Tier W — optional (quota permitting)
* Qwen3-14B, R1-Distill-32B, BGE reranker (already catalog medium)
* Extra quants of models already held in another format
* Code-specific embeds
---
## Explicitly out
* Closed API-only weights
* Full HF org mirrors
* Multiple anonymous “uncensored” reuploads of the same base
---
## Download order (recommended)
1. Pin mount path in backup-storage-policy (done 2026-07-28: `D:\vault\coulomb\freedom-intelligence\`)
2. **R spine** (fast wins, unblocks local work)
3. **S1** — single best open general MoE (compressed if needed)
4. Reassess free space
5. **S4** or **S2** next depending on which niche matters more for Coulomb
6. W-tier only with ≥200 GiB free under soft quota
---
## Catalog
R and selected S/W candidates live under `inventory/catalog/`. Strategic S
entries use tags `tier-s`, `strategic`, `beyond-run-envelope`.