{"as_of":"2026-10-12","license":"CC-BY-4.0","license_url":"https://creativecommons.org/licenses/by/4.0/","cite_as":"The Local Bench (thelocalbench.com), data as of 2026-10-12, CC BY 4.0","source_url":"https://thelocalbench.com","hardware":{"id":"macbook-pro-m4-max-128g","name":"MacBook Pro M4 Max 40c · 128 GB","vendor":"Apple","class":"Apple unified","kind":"unified","as_of":"2026-10-12","summary":"A laptop with twice Strix Halo's bandwidth. MLX and Metal llama.cpp are both mature.","memory_gb":{"value":128,"flag":"sourced","unit":"GB","source":"https://support.apple.com/en-us/121553","note":"Configurable to 128 GB on the 16-core-CPU/40-core-GPU M4 Max, Apple tech specs, checked 2026-10-12."},"bandwidth_gbs":{"value":546,"flag":"sourced","unit":"GB/s","source":"https://support.apple.com/en-us/121553","note":"Vendor spec page, checked 2026-10-12."},"fp16_tflops":{"value":34,"flag":"sample","unit":"TFLOPS","note":"Sample FP16 dense compute; pending vendor-sheet citation."},"host_ram_gb":{"value":0,"flag":"sample","unit":"GB","note":"Assumed host RAM for offload."},"host_bandwidth_gbs":{"value":546,"flag":"sourced","unit":"GB/s","source":"https://support.apple.com/en-us/121553","note":"Unified memory."},"load_watts":{"value":140,"flag":"sample","unit":"W","note":"Sample wall power under load."},"price_usd":{"value":4699,"flag":"sample","unit":"USD","note":"Sample price."},"apple":true,"price_cad":{"value":6705.94,"flag":"sample","unit":"CAD","source":"https://www.bankofcanada.ca/valet/observations/FXUSDCAD/json?recent=1","note":"USD price × 1.4271 (Bank of Canada USD/CAD, 2026-10-09); no Canadian retail listing captured. Converted from a sample USD value."}},"runs":[{"model":"gemma-3-27b","hardware":"macbook-pro-m4-max-128g","quant":"Q4_K_M","runtime":"llama.cpp (Metal)","test":"tg128 @ 8k depth","tok_s":13.9,"min":13.5,"max":14.2,"repeats":5,"flag":"sample","date":"2026-10-12","note":"Placeholder figure from the approved mockup; not a measurement."},{"model":"gemma-3-27b","hardware":"macbook-pro-m4-max-128g","quant":"Q4_K_M","runtime":"llama.cpp","test":"tg128 @ depth 0","depth":0,"tok_s":13.9,"flag":"sample","date":"2026-10-12","note":"Placeholder depth curve from the mockup."},{"model":"gemma-3-27b","hardware":"macbook-pro-m4-max-128g","quant":"Q4_K_M","runtime":"llama.cpp","test":"tg128 @ depth 4096","depth":4096,"tok_s":13.1,"flag":"sample","date":"2026-10-12","note":"Placeholder depth curve from the mockup."},{"model":"gemma-3-27b","hardware":"macbook-pro-m4-max-128g","quant":"Q4_K_M","runtime":"llama.cpp","test":"tg128 @ depth 16384","depth":16384,"tok_s":11.2,"flag":"sample","date":"2026-10-12","note":"Placeholder depth curve from the mockup."},{"model":"gemma-3-27b","hardware":"macbook-pro-m4-max-128g","quant":"Q4_K_M","runtime":"llama.cpp","test":"tg128 @ depth 32768","depth":32768,"tok_s":9.4,"flag":"sample","date":"2026-10-12","note":"Placeholder depth curve from the mockup."},{"model":"llama-2-7b","hardware":"macbook-pro-m4-max-128g","quant":"Q4_0","runtime":"llamafile (Metal)","test":"LocalScore generation","tok_s":62.5,"flag":"sourced","source":"https://www.localscore.ai/model/1248","date":"2026-10-12","note":"Third-party measurement used to calibrate η (brief §4.3): implies η ≈ 0.43."},{"model":"llama-2-7b","hardware":"macbook-pro-m4-max-128g","quant":"Q4_0","runtime":"llama.cpp (Metal)","test":"tg128","tok_s":83.06,"flag":"sourced","date":"2026-10-12","source":"https://github.com/ggml-org/llama.cpp/discussions/4167","note":"Llama 2 7B Q4_0, llama-bench tg128, M4 Max 40-core GPU (546 GB/s), pinned commit 8e672ef (Nov 2023) for comparability; newer builds are faster."}]}