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%
-
Wed, Aug 12, 2026 5
-
candidate_01: W=64 lever NEGATIVE — rollback rate bounds sweep amortization
…
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
-
candidate_01 32B scale run: charter 16.A/B demonstrated in prototype form
…
q8-32B (does not fit beside base on 48 GB) streamed at ~11.6 GB/s sequential; +0.28 nats over pure-q4 (only fitting alternative); 3.72 GB/token logical (9.4x under checkpoint); 1.69 tok/s with measured headroom. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
-
candidate_01 v2 results: q8-equivalent quality with q4 resident (bf16 judge)
…
verify-all -0.1297 vs pure-q8 -0.1328 at 237 MB/token (9x under checkpoint); tunable tau continuum 47%/83%/100% of quality gap. Charter 16.D/E criteria met at 1.7B scale. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
-
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>
-
candidate_01: margin-gated deferred-refinement runtime + benchmark + hypothesis
…
q4 resident base generates with margin recording; low-margin tokens deferred; windowed q8 sweeps verify (margin mode) or verify-all (QSpec-style exact); rollback via KV trim. Baselines: pure q4/q8. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
-