M3 Pro (18 GB) — benchmark record

M3 Pro (18 GB) local LLM benchmarks on Apple Silicon Mac with 2 published rows across 2 models. Peak published speed is 88.0 tok/s on Gemma 3 4B. Published runtimes include MLX, Ollama. Evidence state and next-step ranking links included.

2Benchmark rows

2Models tested

88.0Fastest avg tok/s (Gemma 3 4B)

0Silicon Score Lab rows

What this page answers best

Best published speed here is 88.0 tok/s on Gemma 3 4B at Q4_K - Medium. This page is evidence, not the full buying answer.

Evidence state: 2 linked reference rows and no Silicon Score Lab rows yet.

Published runtimes here: MLX, Ollama.

Need a recommendation? Use Buy Checking a target model? Use Fit Want a setup answer? Use Run Browse Macs by exact hardware Need the full audit trail? Use Bench

Current published coverage

Published model coverage includes Gemma 3 4B, Llama 3.1 8B. Published runtime coverage on this chip includes MLX, Ollama. Fastest published row is 88.0 tok/s on Gemma 3 4B at Q4_K - Medium.

Gemma 3 4B Llama 3.1 8B

Raw benchmark rows for M3 Pro (18 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
Gemma 3 4B	Q4_K - Medium	—	—	88.0 tok/s	—	MLX	ref
Llama 3.1 8B	Q4_K - Medium	—	—	62.0 tok/s	—	Ollama	ref

Models tested on this chip

Gemma 3 4B Llama 3.1 8B

Next step

Use Rankings when you need the best overall answer for a Mac, and keep this page open when you need the evidence behind that recommendation.

If you are comparing local Apple Silicon against rented cloud hardware, use AI Data Center Index for current GPU rental context.

Data

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

Data sourced from Silicon Score Lab measurements and community reference runs. See all chip families →