M2 Max (38-core GPU, 96 GB) — LLM Benchmarks

Measured LLM inference benchmarks for M2 Max (38-core GPU, 96 GB). Tokens per second across 2 models and multiple quantizations. Real runs, not estimates.

2 Benchmark rows

2 Models tested

46.4 Fastest avg tok/s (Llama 3.1 8B Instruct)

0 Factory-lab verified rows

Benchmark results for M2 Max (38-core GPU, 96 GB)

Rows sorted by avg tok/s descending. Click source badge to see original measurement page.

Model	Quant	RAM req.	Context	Avg tok/s	Prompt tok/s	Runtime	Source
Llama 3.1 8B Instruct	Q4_K - Medium	—	—	46.4 tok/s	484.1 tok/s	—	ref
Qwen 2.5 14B Instruct	Q4_K - Medium	—	—	25.2 tok/s	252.5 tok/s	—	ref

Models tested on this chip

Llama 3.1 8B Instruct Qwen 2.5 14B Instruct

Data

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

Want to contribute a benchmark for this chip? Data sourced from factory lab measurements and community reference runs. See all chips →