Apple M5 Max (40-core GPU, 128GB)

Compare Apple M5 Max (40-core GPU, 128GB) against another machine in the Arena

Class: Mac
Memory: 128 GB LPDDR5X
Runs (Q4_K_M): —
Bandwidth: 614 GB/s
Released: 2026-03-11
Price (US): $6699 new as of 2026-06
Price (Canada): CA$9699 new sourced, as of 2026-08

Sourcing and disambiguation notes

MacBook Pro 14-inch, M5 Max 18-core CPU/40-core GPU, 128GB/2TB. Same 2026-06-25 price-increase basis as the 64GB config (128GB upgrade rose from +$1,000 to +$2,000 over the $4,699 base) -- postdates the June 2026 memory shortage. Cross-checked against B&H Photo pricing seen 2026-08-18 ($6,699 MSRP / $6,499 sale), which matched exactly. Canadian price (2026-08, pre-tax): CA$9,699 from the live apple.com/ca configurator for MacBook Pro 14" M5 Max (18-core CPU / 40-core GPU) 128GB/2TB, the same configuration as the US entry, confirmed by direct page fetch 2026-08-22. Ratio to the US $6,699 is 1.45x.

Specification sources

https://github.com/ggml-org/llama.cpp/discussions/4167 — community-table, 2026-03-31
https://www.apple.com/macbook-pro/specs/ — vendor, 2026-08-22

Measurements

Decode is token generation — the speed you feel while an answer streams. Prefill is prompt processing — the wait before it starts. Why bandwidth predicts decode speed.

What verified, single-source and estimated mean, and the same rows with every filter and sort in the benchmarks explorer.

Speed over time

What it can run

Fit is arithmetic, not a measurement — how it is computed. Against 128 GB; models that fit are listed largest first.