← Quests
Quest Fitq_private_localpeer min-max inputs
Private Local Coding
Hard-filters to local runtimes. Ranks open local Builds for coding utility, reliability, and practical tool use under hardware constraints. Cloud flagships are disqualified even if stronger on public benchmarks.
SharePost on X
How to read this
Fit score ≠ absolute IQ
- Fit score is a weighted blend of this Quest’s attribute/skill weights (and optional cost/tempo soft prefs). Higher = better match for this job among scored Builds.
- Attribute inputs are peer-public scores (roughly 40–95 within the current peer set). A low STR here can still be a strong absolute model — it just ranks lower among current scored peers on that axis.
- Decisive means the leader is ≥4 fit points ahead of #2. Smaller gaps → pick on price, Party stack, or taste.
Peer set today: 6 scored Builds. Adding another re-ranks peers — re-run the engine after new evidence.
Insufficient scored Builds
No scored Builds pass filters for this Quest yet. Score more launch Builds in the engine, then redeploy.
What matters most
- Real coding utility at the pinned quant
- Runnable on stated hardware class
- Tool/IDE harness compatibility
Common failure modes
- Recommending unquantised 100B+ models as “local” without hardware
- Treating cloud open-weight APIs as private local
- Ignoring quality loss from aggressive quantisation