M1 Pro — benchmark record

M1 Pro local LLM benchmarks across 16 GB RAM tiers on Apple Silicon Mac. 2 published rows across 1 models with explicit evidence state and RAM-tier comparison. Peak published speed is 30.0 tok/s.

2Benchmark rows

1Models tested

1RAM configurations

30.0Fastest avg tok/s

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.

16 GBM1 Pro (16 GB)2 rows · 1 models30.0 tok/s peak

All benchmark rows — M1 Pro

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

Chip (RAM)	Model	Quant	RAM req.	Avg tok/s	Prompt tok/s	Runtime	Source
M1 Pro (16 GB)	Qwen3.5-9B	4bit	—	30.0 tok/s	—	MLX	ref
M1 Pro (16 GB)	Qwen3.5-9B	4bit	—	15.0 tok/s	—	llama.cpp	ref

Models tested on M1 Pro

Qwen3.5-9B

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 →