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.
Quick take
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.
Current published coverage
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.
Macs shipping with the M5 Max (48 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.
| Model | Quant | Avg tok/s | Runtime | Source |
|---|---|---|---|---|
| Qwen3.5-35B-A3B | 4bit | 128.0 tok/s | MLX | ref |
| Qwen3.5-35B-A3B | Q4_K - Medium | 89.4 tok/s | llama.cpp | ref |
| Qwen3.5-27B | 4bit | 31.3 tok/s | MLX | ref |
| Qwen3.5-27B | Q4_K - Medium | 23.7 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 →