← Canonical rankings

M4 Pro (16-core GPU) — benchmark record

M4 Pro (16-core GPU) local LLM benchmarks across 24 GB, 48 GB, 64 GB RAM tiers on Apple Silicon Mac. 8 published rows across 3 models with explicit evidence state and RAM-tier comparison. Peak published speed is 111.9 tok/s.

8Benchmark rows
3Models tested
3RAM configurations
111.9Fastest avg tok/s

Each configuration differs only in unified memory. More RAM = larger models fit. Throughput is similar across RAM tiers at the same model size.

All benchmark rows — M4 Pro (16-core GPU)

Sorted by avg tok/s descending. Click source badge to see original measurement.

Chip (RAM)ModelQuantRAM req.Avg tok/sPrompt tok/sRuntimeSource
M4 Pro (16-core GPU, 64 GB)Llama 3.2 1BQ4_K - Medium111.9 tok/s1858.9 tok/sllamafileref
M4 Pro (16-core GPU, 48 GB)Llama 3.2 1BQ4_K - Medium111.0 tok/s1754.6 tok/sllamafileref
M4 Pro (16-core GPU, 24 GB)Llama 3.2 1BQ4_K - Medium110.9 tok/s1823.8 tok/sllamafileref
M4 Pro (16-core GPU, 24 GB)Llama 3.1 8BQ4_K - Medium30.5 tok/s298.0 tok/sllamafileref
M4 Pro (16-core GPU, 48 GB)Llama 3.1 8BQ4_K - Medium30.2 tok/s302.4 tok/sllamafileref
M4 Pro (16-core GPU, 48 GB)Qwen 2.5 14BQ4_K - Medium16.8 tok/s161.1 tok/sllamafileref
M4 Pro (16-core GPU, 64 GB)Qwen 2.5 14BQ4_K - Medium16.1 tok/s151.0 tok/sllamafileref
M4 Pro (16-core GPU, 24 GB)Qwen 2.5 14BQ4_K - Medium15.2 tok/s144.3 tok/sllamafileref

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 →