Silicon Score › Chips › M4 (GPU count not published)

M4 (GPU count not published) — LLM Benchmarks

Measured LLM inference benchmarks for M4 (GPU count not published) across all RAM configurations (16 GB). 1 benchmark rows across 1 models. Compare how RAM affects throughput. Real runs, not estimates.

RAM configurations

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.

Models tested on M4 (GPU count not published)

Data

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

Data sourced from factory lab measurements and community reference runs. See all chips →