← Canonical rankings

M4 Max (48 GB) — benchmark record

M4 Max (48 GB) local LLM benchmarks on Apple Silicon Mac with 3 published rows across 3 models. Peak published speed is 42.0 tok/s on Qwen3.6-35B-A3B. Published runtimes include MLX. Evidence state and next-step ranking links included.

3Benchmark rows
3Models tested
42.0Fastest avg tok/s (Qwen3.6-35B-A3B)
0Silicon Score Lab rows

Best published speed here is 42.0 tok/s on Qwen3.6-35B-A3B at Q4_K - Medium. This page is evidence, not the full buying answer.

Evidence state: 3 linked reference rows and no Silicon Score Lab rows yet.

Published runtimes here: MLX.

Published model coverage includes Qwen3.6-35B-A3B, Gemma 4 26B-A4B, Gemma 4 31B. Published runtime coverage on this chip includes MLX. Fastest published row is 42.0 tok/s on Qwen3.6-35B-A3B at Q4_K - Medium.

Other published M4 Max variants: GB · 128 GB

This chip is part of a family. Compare all M4 Max RAM variants →

Raw benchmark rows for M4 Max (48 GB)

Rows sorted by avg tok/s descending. Click source badge to see original measurement page.

ModelQuantRAM req.ContextAvg tok/sPrompt tok/sRuntimeSource
Qwen3.6-35B-A3BQ4_K - Medium42.0 tok/sMLXref
Gemma 4 26B-A4BQ4_K - Medium40.0 tok/sMLXref
Gemma 4 31BQ4_K - Medium18.0 tok/sMLXref

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.

benchmarks.json — full dataset  ·  chips.json — chip summaries  ·  benchmarks.csv — CSV export

Data sourced from Silicon Score Lab measurements and community reference runs. See all chip families →