M5 Pro (64 GB) — benchmark record

M5 Pro (64 GB) local LLM benchmarks on Apple Silicon Mac with 4 published rows across 4 models. Peak published speed is 41.9 tok/s on Qwen3.5-35B-A3B. Largest published fit uses 40.8 GB. Published runtimes include llama.cpp.

4Benchmark rows

4Models tested

41.9Fastest avg tok/s (Qwen3.5-35B-A3B)

0Lab benchmarks

Quick take

Best published speed here is 41.9 tok/s on Qwen3.5-35B-A3B at Q4_K_L. Largest published memory footprint is Qwen3.5-122B-A10B at IQ1_M, using 40.8 GB. This page is evidence, not the full buying answer.

Based on 4 external benchmarks; no lab runs yet.

Published runtimes: llama.cpp.

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 Qwen3.5-35B-A3B, Qwen3.5-9B, Qwen3.5-122B-A10B, Qwen3.5-27B. Published runtime coverage on this chip includes llama.cpp. Fastest published row is 41.9 tok/s on Qwen3.5-35B-A3B at Q4_K_L. Largest published footprint on this page is 40.8 GB for Qwen3.5-122B-A10B.

Qwen3.5-35B-A3B Qwen3.5-9B Qwen3.5-122B-A10B Qwen3.5-27B

Other published M5 Pro variants: 24 GB

This chip is part of a family. Compare all M5 Pro RAM variants →

Raw benchmark rows for M5 Pro (64 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
Qwen3.5-35B-A3B	Q4_K_L	27.2 GB	—	41.9 tok/s	—	llama.cpp	ref
Qwen3.5-9B	Q4_K - Medium	13.8 GB	—	25.0 tok/s	—	llama.cpp	ref
Qwen3.5-122B-A10B	IQ1_M	40.8 GB	—	18.0 tok/s	—	llama.cpp	ref
Qwen3.5-27B	Q4_K - Medium	24.9 GB	—	10.0 tok/s	—	llama.cpp	ref

Models tested on this chip

Qwen3.5-35B-A3B Qwen3.5-9B Qwen3.5-122B-A10B Qwen3.5-27B

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 →