M2 (8 GB) — benchmark record

M2 (8 GB) local LLM benchmarks on Apple Silicon Mac with 3 published rows across 3 models. Peak published speed is 72.0 tok/s on Phi-4 Mini Instruct 3.8B. Published runtimes include Ollama.

3Benchmark rows

3Models tested

72.0Fastest avg tok/s (Phi-4 Mini Instruct 3.8B)

0Lab benchmarks

Quick take

Best published speed here is 72.0 tok/s on Phi-4 Mini Instruct 3.8B at Q4_K - Medium. This page is evidence, not the full buying answer.

Based on 3 external benchmarks; no lab runs yet.

Published runtimes: 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 Phi-4 Mini Instruct 3.8B, Qwen 3 4B, Llama 3.1 8B. Published runtime coverage on this chip includes Ollama. Fastest published row is 72.0 tok/s on Phi-4 Mini Instruct 3.8B at Q4_K - Medium.

Phi-4 Mini Instruct 3.8B Qwen 3 4B Llama 3.1 8B

Other published M2 variants: 16 GB · 24 GB

This chip is part of a family. Compare all M2 RAM variants →

Raw benchmark rows for M2 (8 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
Phi-4 Mini Instruct 3.8B	Q4_K - Medium	—	—	72.0 tok/s	—	Ollama	ref
Qwen 3 4B	Q4_K - Medium	—	—	52.0 tok/s	—	Ollama	ref
Llama 3.1 8B	Q4_K - Medium	—	—	48.0 tok/s	—	Ollama	ref

Models tested on this chip

Phi-4 Mini Instruct 3.8B Qwen 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 from in-house lab measurements plus community-published benchmarks. See all chip families →