M2 Pro (16-core GPU) — LLM Benchmarks

Measured LLM inference benchmarks for M2 Pro (16-core GPU) across all RAM configurations (16 GB, 32 GB). 5 benchmark rows across 3 models. Compare how RAM affects throughput. Real runs, not estimates.

5Benchmark rows

3Models tested

2RAM configurations

91.5Fastest 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 GBM2 Pro (16-core GPU, 16 GB)3 rows · 3 models91.2 tok/s peak 32 GBM2 Pro (16-core GPU, 32 GB)2 rows · 2 models91.5 tok/s peak

All benchmark rows — M2 Pro (16-core GPU)

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
M2 Pro (16-core GPU, 32 GB)	Llama 3.2 1B Instruct	Q4_K - Medium	—	91.5 tok/s	1281.4 tok/s	—	ref
M2 Pro (16-core GPU, 16 GB)	Llama 3.2 1B Instruct	Q4_K - Medium	—	91.1 tok/s	1328.2 tok/s	—	ref
M2 Pro (16-core GPU, 16 GB)	Llama 3.1 8B Instruct	Q4_K - Medium	—	24.3 tok/s	224.6 tok/s	—	ref
M2 Pro (16-core GPU, 32 GB)	Llama 3.1 8B Instruct	Q4_K - Medium	—	23.8 tok/s	208.7 tok/s	—	ref
M2 Pro (16-core GPU, 16 GB)	Qwen 2.5 14B Instruct	Q4_K - Medium	—	13.4 tok/s	119.0 tok/s	—	ref

Models tested on M2 Pro (16-core GPU)

Llama 3.1 8B Instruct Llama 3.2 1B Instruct Qwen 2.5 14B Instruct

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 →