# Recommend thinking budget 512 for the deep tier

> Living preprint · as of 2026-10-25 · map node D-056 (decision) · interim record, not a final result.

<!-- lint:exempt:start -->
- [D-056] 2026-10-09 · Recommend thinking budget 512 for the deep tier · why: CHEAPER-PARITY with 1024 at 0.55× time. · status: kept

<!-- lint:exempt:end -->
## Incoming

- led to: [X-095] DT512: DT512 (512 tokens = 1024 at about half the time) → https://r4topunk.github.io/boar-research/map/x-095.md

Read chapter 6, The deep tier: https://r4topunk.github.io/boar-research/research/deep-tier.md

## Facts cited {#facts}

Resolve every [F-…] marker in https://r4topunk.github.io/boar-research/data/facts.json. Each line gives the claim, the number with its metric family, set and status, judge, n, seeds, CI, date and caveat.

<!-- lint:exempt:start -->
- [F-598] Recommend thinking budget 512 for the deep tier — why: CHEAPER-PARITY with 1024 at 0.55× time — outcome: becomes the "recommended deep configuration" · date 2026-10-09
- [F-599] Recommend deep tier = cut 6 + Qwen3.6-35B-A3B + thinking budget 512 (why: DT512 CHEAPER-PARITY: = 1024 quality at 0.55× time) · date 2026-10-09 · caveat: outcome: Became row H everywhere; selected best of ≥ 8 deep configs on V-para (winner's-curse ≈ 0.01–0.02)
- [F-748] Recommended deep config = cut 6 + Qwen3.6-35B-A3B UD-Q2_K_XL + thinking budget 512 (why: 512 = 1024 in quality at 0.55× time) · date 2026-10-09 · caveat: outcome: not in claim build; needs a 12 GB device and an app-side thinking cap

<!-- lint:exempt:end -->
---

Cite as: r4to, independent researcher. RatLab — A Boar Research (2026), research record 1.0, as of 2026-10-25. Text and data CC BY 4.0. Fact ids or a link must travel with a quote. How to cite: https://r4topunk.github.io/boar-research/cite/ · https://r4topunk.github.io/boar-research/CITATION.cff.

AI-reviewed, not clinically reviewed. Nothing here is medical advice.