M4 Max — benchmark record
M4 Max local LLM benchmarks on Apple Silicon Mac with 3 published rows across 1 models. Peak published speed is 16.7 tok/s on Qwen3.5-27B. Largest published fit uses 16.4 GB. Published runtimes include llama.cpp.
Quick take
Best published speed here is 16.7 tok/s on Qwen3.5-27B at Q4_K. Largest published memory footprint is Qwen3.5-27B at Q4_K, using 16.4 GB. Longest published context on this page is 16k. This page is evidence, not the full buying answer.
Based on 3 external benchmarks; no lab runs yet.
Published runtimes: llama.cpp.
Current published coverage
Published model coverage includes Qwen3.5-27B. Published runtime coverage on this chip includes llama.cpp. Fastest published row is 16.7 tok/s on Qwen3.5-27B at Q4_K. Largest published footprint on this page is 16.4 GB for Qwen3.5-27B. Longest published context is 16k.
Macs shipping with the M4 Max
This chip is part of a family. Compare all M4 Max RAM variants →
Raw benchmark rows for M4 Max
Rows sorted by avg tok/s descending. Click source badge to see original measurement page.
| Model | Quant | Avg tok/s | Runtime | Source |
|---|---|---|---|---|
| Qwen3.5-27B | Q4_K | 16.7 tok/s | llama.cpp | ref |
| Qwen3.5-27B | Q4_K | 16.1 tok/s | llama.cpp | ref |
| Qwen3.5-27B | Q4_K | 15.8 tok/s | llama.cpp | ref |
Models tested on this chip
Next step
Use Rankings when you need the best overall answer for a Mac, and keep this page open when you need the evidence behind that recommendation.
If you are comparing local Apple Silicon against rented cloud hardware, use AI Data Center Index for current GPU rental context.
Data
benchmarks.json — full dataset · chips.json — chip summaries · benchmarks.csv — CSV export
Data from in-house lab measurements plus community-published benchmarks. See all chip families →