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%
1loading reference mlx-community/Qwen3-1.7B-bf16 …2
Fetching 9 files: 0%| | 0/9 [00:00<?, ?it/s]
Fetching 9 files: 100%|██████████| 9/9 [00:00<00:00, 6401.35it/s]348 reference trajectories in 49s4building ladder A_base3 [3, 3, 3] …5 stage 0 (4.0 bits): agree=0.7321 KL=0.7781 auroc=0.8506 stage 1 (8.0 bits): agree=0.9569 KL=0.0240 auroc=0.9527 stage 2 (12.0 bits): agree=0.9827 KL=0.0023 auroc=0.9808building ladder B_base4 [4, 4] …9 stage 0 (5.0 bits): agree=0.8753 KL=0.1982 auroc=0.89510 stage 1 (10.0 bits): agree=0.9842 KL=0.0031 auroc=0.9761112wrote /Users/simon-pierreboucher/Desktop/localvm-research/results/expD_progressive_reconstruction/20260812T043508Z/results.json13