← Canonical rankings

M4 (GPU count not published) — benchmark record

M4 (GPU count not published) local LLM benchmarks across 16 GB RAM tiers on Apple Silicon Mac. 1 published rows across 1 models with explicit evidence state and RAM-tier comparison. Peak published speed is 68.0 tok/s.

1Benchmark rows
1Models tested
1RAM configurations
68.0Fastest 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 (GPU count not published)

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

Chip (RAM)ModelQuantRAM req.Avg tok/sPrompt tok/sRuntimeSource
M4 (GPU count not published, 16 GB)Llama 3.2 1BQ4_K - Medium68.0 tok/s239.0 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 →