SPB Git

spb/modelmap Public License

Internal cartography of local LLMs on Apple Silicon — registered, gated, negative-first. Public atlas at modelmap.io.

Python 66.3% JavaScript 24.5% CSS 8.1% Shell 0.7%
5.5 KB · 253 lines json
Raw Blame History
1{2  "experiment": "expH_capture_cost_frontier",3  "run": 1,4  "scope": "storage formats (warm cache) + capture overhead, synthetic model",5  "commit": "18bd626391ff0edd868a0c2e3d257df055247b55",6  "config": {7    "storage": {8      "rows": 100000,9      "dim": 4096,10      "write_chunk": 4096,11      "batch": 4096,12      "n_batches": 24,13      "repeats": 3,14      "cache": "warm (declared limitation; cold pass = run #2)"15    },16    "compute": {17      "layers": 12,18      "d_model": 1024,19      "heads": 4,20      "seq": 512,21      "batch": 8,22      "dtype": "float16",23      "n_forwards": 20,24      "warmup": 3,25      "repeats": 326    },27    "seed": 028  },29  "manifest": {30    "author": "Simon-Pierre Boucher",31    "contact": "contact@spboucher.ai",32    "website": "https://modelmap.io",33    "chip": {34      "brand": "Apple M5 Max",35      "cores_total": 18,36      "cores_performance": 6,37      "cores_efficiency": 1238    },39    "memory": {40      "unified_gb": 48.0,41      "pagesize": 1638442    },43    "os": {44      "system": "Darwin",45      "version": "27.0",46      "arch": "arm64"47    },48    "software": {49      "python": "3.14.4",50      "numpy": "2.5.2",51      "mlx": "0.32.0",52      "torch": "2.13.0",53      "safetensors": "0.8.0"54    }55  },56  "storage": [57    {58      "format": "raw-mmap",59      "op": "write",60      "bytes": 819200000,61      "seconds": [62        0.22015058299984958,63        0.2848355409996657,64        0.3059425000001283565      ],66      "gb_per_s_mean": 2.822465863994468667    },68    {69      "format": "raw-mmap",70      "op": "seq-scan",71      "bytes": 819200000,72      "seconds": [73        0.16795029199965938,74        0.10112945800028683,75        0.1064520829995672176      ],77      "gb_per_s_mean": 6.09487174787114878    },79    {80      "format": "raw-mmap",81      "op": "random-batch",82      "bytes": 805306368,83      "seconds": [84        0.1789496669998698,85        0.1846267920000173,86        0.186362999999801187      ],88      "gb_per_s_mean": 4.091359445442658589    },90    {91      "format": "safetensors",92      "op": "write",93      "bytes": 819200000,94      "seconds": [95        0.11196637499961071,96        0.08140020800055936,97        0.089228207999440298      ],99      "gb_per_s_mean": 8.09929422718254100    },101    {102      "format": "safetensors",103      "op": "seq-scan",104      "bytes": 819200000,105      "seconds": [106        0.10347433399965666,107        0.10620929100059584,108        0.1054912500003411109      ],110      "gb_per_s_mean": 7.262058434609323111    },112    {113      "format": "safetensors",114      "op": "random-batch",115      "bytes": 805306368,116      "seconds": [117        0.1736507920004442,118        0.176909834000071,119        0.17781483300041145120      ],121      "gb_per_s_mean": 4.258335548464703122    },123    {124      "format": "zarr-uncompressed",125      "op": "write",126      "bytes": 819200000,127      "seconds": [128        0.4914736250002534,129        0.5174622080003246,130        0.524438000000373131      ],132      "gb_per_s_mean": 1.4926682000928473133    },134    {135      "format": "zarr-uncompressed",136      "op": "seq-scan",137      "bytes": 819200000,138      "seconds": [139        0.16390270800002327,140        0.15708874999927502,141        0.1571942090004086142      ],143      "gb_per_s_mean": 4.78646374688684144    },145    {146      "format": "zarr-uncompressed",147      "op": "random-batch",148      "bytes": 805306368,149      "seconds": [150        0.5920942090006065,151        0.6018026250003459,152        0.5726199580003595153      ],154      "gb_per_s_mean": 1.2736929590411328155    },156    {157      "format": "zarr-zstd",158      "op": "write",159      "bytes": 819200000,160      "seconds": [161        1.582709333000821,162        1.3768872919999922,163        1.252639000000272164      ],165      "gb_per_s_mean": 0.5433737718255992166    },167    {168      "format": "zarr-zstd",169      "op": "seq-scan",170      "bytes": 819200000,171      "seconds": [172        0.24328949999926408,173        0.17038491599942063,174        0.16977412500000355175      ],176      "gb_per_s_mean": 3.922913845079177177    },178    {179      "format": "zarr-zstd",180      "op": "random-batch",181      "bytes": 805306368,182      "seconds": [183        2.0657694999999876,184        1.9662967499998558,185        1.9579576249998354186      ],187      "gb_per_s_mean": 0.3756245462377428188    }189  ],190  "compute": [191    {192      "backend": "torch-mps",193      "mode": "plain",194      "s_per_forward": [195        0.04537852500002373,196        0.045744383349983764,197        0.04896532289999413198      ],199      "tokens_per_s_mean": 87716.14781880443200    },201    {202      "backend": "torch-mps",203      "mode": "retain",204      "s_per_forward": [205        0.053923208349988275,206        0.05791100205001385,207        0.05981330204999722208      ],209      "tokens_per_s_mean": 71588.57023098122210    },211    {212      "backend": "torch-mps",213      "mode": "retain+copy+write",214      "s_per_forward": [215        0.07440289169999233,216        0.06590515420002703,217        0.06603583339992838218      ],219      "tokens_per_s_mean": 59551.075814261436220    },221    {222      "backend": "mlx",223      "mode": "plain",224      "s_per_forward": [225        0.03250455415000033,226        0.03844294169998648,227        0.03760368125003879228      ],229      "tokens_per_s_mean": 113200.0622036286230    },231    {232      "backend": "mlx",233      "mode": "retain",234      "s_per_forward": [235        0.0370830708000085,236        0.036970339600020455,237        0.03677087500000198238      ],239      "tokens_per_s_mean": 110878.22453034802240    },241    {242      "backend": "mlx",243      "mode": "retain+copy+write",244      "s_per_forward": [245        0.044162579200019536,246        0.03750625419997959,247        0.03900341250000565248      ],249      "tokens_per_s_mean": 101829.54587737157250    }251  ]252}253