← Canonical rankings

M5 Max (48 GB) — benchmark record

M5 Max (48 GB) local LLM benchmarks on Apple Silicon Mac with 4 published rows across 2 models. Peak published speed is 128.0 tok/s on Qwen3.5-35B-A3B. Published runtimes include llama.cpp, MLX.

4Benchmark rows
2Models tested
128.0Fastest avg tok/s (Qwen3.5-35B-A3B)
0Lab benchmarks

Best published speed here is 128.0 tok/s on Qwen3.5-35B-A3B at 4bit. Longest published context on this page is 8k. This page is evidence, not the full buying answer.

Based on 4 external benchmarks; no lab runs yet.

Published runtimes: llama.cpp, MLX.

Published model coverage includes Qwen3.5-35B-A3B, Qwen3.5-27B. Published runtime coverage on this chip includes llama.cpp, MLX. Fastest published row is 128.0 tok/s on Qwen3.5-35B-A3B at 4bit. Longest published context is 8k.

Other published M5 Max variants: 64 GB · 128 GB

This chip is part of a family. Compare all M5 Max RAM variants →

Raw benchmark rows for M5 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
Qwen3.5-35B-A3B4bit8k128.0 tok/s3235.0 tok/sMLXref
Qwen3.5-35B-A3BQ4_K - Medium8k89.4 tok/s783.0 tok/sllama.cppref
Qwen3.5-27B4bit8k31.3 tok/s779.0 tok/sMLXref
Qwen3.5-27BQ4_K - Medium8k23.7 tok/s171.0 tok/sllama.cppref

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 from in-house lab measurements plus community-published benchmarks. See all chip families →