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/Qwen3-8B-bf16 …2
Fetching 12 files: 0%| | 0/12 [00:00<?, ?it/s]Warning: You are sending unauthenticated requests to the HF Hub. Please set a HF_TOKEN to enable higher rate limits and faster downloads.3
Fetching 12 files: 17%|█▋ | 2/12 [00:00<00:00, 15.49it/s]
Fetching 12 files: 42%|████▏ | 5/12 [00:00<00:00, 18.46it/s]
Fetching 12 files: 58%|█████▊ | 7/12 [00:00<00:00, 17.87it/s]
Fetching 12 files: 67%|██████▋ | 8/12 [00:20<00:00, 17.87it/s]
Fetching 12 files: 75%|███████▌ | 9/12 [00:38<00:20, 6.86s/it]
Fetching 12 files: 83%|████████▎ | 10/12 [01:43<00:37, 18.88s/it]
Fetching 12 files: 92%|█████████▏| 11/12 [01:44<00:14, 14.68s/it]
Fetching 12 files: 100%|██████████| 12/12 [01:50<00:00, 9.21s/it]4 generated code5 generated math6 generated chat7 generated french8 generated english9 generated reasoning10reference generation done in 194s (48 trajectories)11quantizing to 3-bit (group 64) …12
Fetching 12 files: 0%| | 0/12 [00:00<?, ?it/s]
Fetching 12 files: 100%|██████████| 12/12 [00:00<00:00, 7472.04it/s]13 3-bit: agree=0.8527 AUROC=0.883 esc@99%=0.409830729166666714quantizing to 4-bit (group 64) …15
Fetching 12 files: 0%| | 0/12 [00:00<?, ?it/s]
Fetching 12 files: 100%|██████████| 12/12 [00:00<00:00, 2337.96it/s]16 4-bit: agree=0.9212 AUROC=0.920 esc@99%=0.2260742187517quantizing to 8-bit (group 64) …18
Fetching 12 files: 0%| | 0/12 [00:00<?, ?it/s]
Fetching 12 files: 100%|██████████| 12/12 [00:00<00:00, 6075.77it/s]19 8-bit: agree=0.9867 AUROC=0.981 esc@99%=0.0159505208333333322021wrote /Users/simon-pierreboucher/Desktop/localvm-research/results/expG_decision_stability/20260812T051129Z/results.json22