SPB Git

spb/localvm-research Public License

Running LLMs larger than memory on a consumer Mac — falsification-driven research: margin-gated deferred refinement, out-of-core verification on Apple Silicon. TR-01 published.

Python 63.2% JavaScript 23.5% CSS 11.8% Shell 0.9% Makefile 0.5%

History of experiments/micro/expG_decision_stability/analysis.md · clear filter

  1. expG@8B: favorable scaling; candidate_01 first run: bytes pass, metric insight
    …
    8B: esc@99% falls to 22.6% at 4-bit. Candidate: 154-231 MB/token logical
(9-14x under checkpoint); verify-all at hardware ceiling (q8 self-
agreement 1.56%/token prefill/decode flips); margin-mode seq-fidelity
fails as registered -> quality-level metrics now mandatory.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
    Simon-Pierre Boucher committed 6 h ago (Aug 12, 2026) · 1 file changed +20
  2. expG: full results — margin gating promoted (AUROC 0.85-0.98), affine 2-bit base dead
    …
    48 trajectories x 4 bit-widths on Qwen3-1.7B; esc@99%: 60/37/5% at
3/4/8-bit; ParetoQ cliff confirmed at naive 2-bit (3% agreement).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
    Simon-Pierre Boucher committed 7 h ago (Aug 12, 2026) · 1 file changed +62 −3
  3. Bootstrap: charter-compliant skeleton, header enforcement, hardware manifest, experiment scaffolds
    …
    - Repository layout per CLAUDE.md §3
- tools/check_headers.py enforcing §0.1 (58 files pass)
- tools/new_experiment.py scaffolding with seven-field hypothesis block (§10)
- benchmarks/hardware_manifest.py: macOS-native fingerprint (M5 Max / 48GB verified)
- Eight micro-experiment scaffolds (§9, exp A–H)

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
    Simon-Pierre Boucher committed 8 h ago (Aug 12, 2026) · 1 file changed +12