KINGY.AI← Local AI planner

LOCAL AI / PRACTICAL TASKS

Choose a job.
Check its exact setup.

Compare your selected computer and settings with retained task runs. Download a public sample, run its original verifier and use version-scoped troubleshooting when it fails.

Invoice extraction and cited PDF search have narrow, dated Mac evidence. The coding path provides a frozen fixture and checker; model execution is currently deferred by the Mac resource guard. Existing corrected-note kits remain available.

All existing work kits and local answer checkers →

1. Select your hardware and runtime

These are declared settings. This page does not scan or test your computer. Defaults display the retained Mac setup so you can inspect its evidence; change every value that differs.

Exact artifact: official Qwen3-4B Q4_K_M, 2,497,280,256 bytes. One complete GGUF, revision bc640142c66e1fdd12af0bd68f40445458f3869b. Pinned model source.

Fixed tested execution settings: CPU only; 4 inference threads, 4 batch threads, F16 K/V, one slot. Retained invoice/PDF samples use Python 3.12.14; PDF parsing requires pypdf 6.10.0. Coding checker uses Python 3.14.0. Model downloads and runtime installation are intentional setup steps; this page downloads neither.

Memory fit and compatibility are separate

Exact CPU memory fit: insufficient information. Low/high allocation, headroom and capacity reserves are unavailable for this CPU task configuration in the retained shared estimator. Process RSS in a task receipt is not a capacity requirement. No fit or speed verdict is inferred from the file size or a task pass.

The existing shared estimator covers other supported execution settings. Open hardware/model planning · Local Lab estimator and sources. Changing context or model requires recalculation there and task requalification here.

2. Choose a task and its original verifier

Extract an invoice

Turn a small text invoice into four typed fields, preserving a missing bank account as null.

One public synthetic sample passed on 2026-10-28 UTC; 4.181 s answer time and 5.912 s startup. This is dated shared-machine observation, not a general quality or speed estimate.

Download retained working sample kit ↓ · Check the public sample locally

ZIP 64,563 bytes. SHA-256 0758666b59956cf5207b731f4ccf067b241a4703f2d698946fe8b6f98b08e44d

A self-test failed → inspect matching troubleshooting

Repair integer billing rounding

One public Python fixture; one fixed change; original seven tests. No general coding ability claim.

No model task run: preflight deferred 2026-10-29 UTC because memory pressure was 2. The original broken fixture fails its tests; a checker reference implementation passes. Those checker tests do not qualify the model.

Download coding fixture and checker (unqualified) ↓ · Inspect coding manifest

ZIP 10,927 bytes. SHA-256 5e125a7d7cf9f4fd5fd7a5a7c716567d930a90bb9f2ea852cf961ffc2360aeb8

A self-test failed → inspect matching troubleshooting

3. Diagnose, then rerun the original task

These existing Fix Finder records retain their own exact task and settings. A matching runtime is a reference, not a reproduced repair for your task. Keep the original failure; apply only a supported correction; recalculate changed memory settings; rerun the unchanged verifier. No log text or commands are uploaded or executed by this page.

Return to the invoice verifier → · Browse existing Fix Finder diagnostics

Source health and evidence dates

Journey registry 20261029.1 reuses retained task runs dated October 28 UTC. No measurement date is refreshed by packaging, a metadata check or replaying an output. New runtime metadata cannot inherit a task pass.

Versioned task registry (JSON) · Exact pinned metadata and package health. The health report covers source and package integrity only; it does not qualify this machine or a current runtime.

Setup links contain public configuration fields only. No accounts, uploads or per-visitor AI calls. No telemetry is added. A download is not evidence that the reader ran the task.