M1 Ultra (64-core GPU, 128 GB) — LLM Benchmarks

Measured LLM inference benchmarks for M1 Ultra (64-core GPU, 128 GB). Tokens per second across 3 models and multiple quantizations. Real runs, not estimates.

3Benchmark rows

3Models tested

151.1Fastest avg tok/s (Llama 3.2 1B Instruct)

0Factory-lab verified rows

Benchmark results for M1 Ultra (64-core GPU, 128 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 3.2 1B Instruct	Q4_K - Medium	—	—	151.1 tok/s	2977.1 tok/s	—	ref
Llama 3.1 8B Instruct	Q4_K - Medium	—	—	54.3 tok/s	667.6 tok/s	—	ref
Qwen 2.5 14B Instruct	Q4_K - Medium	—	—	32.4 tok/s	371.7 tok/s	—	ref

Models tested on this chip

Llama 3.2 1B Instruct Llama 3.1 8B 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 →