M3 Ultra (60-core GPU, 96 GB) — benchmark record

M3 Ultra (60-core GPU, 96 GB) local LLM benchmarks on Apple Silicon Mac with 1 published rows across 1 models. Peak published speed is 34.4 tok/s on Qwen 2.5 14B. Published runtimes include llamafile.

1Benchmark rows

1Models tested

34.4Fastest avg tok/s (qwen-2-5-14b-instruct)

0Lab benchmarks

Quick take

Best published speed here is 34.4 tok/s on Qwen 2.5 14B at Q4_K - Medium. This page is evidence, not the full buying answer.

Based on 1 external benchmark; no lab runs yet.

Published runtimes: llamafile.

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 Qwen 2.5 14B. Published runtime coverage on this chip includes llamafile. Fastest published row is 34.4 tok/s on Qwen 2.5 14B at Q4_K - Medium.

Qwen 2.5 14B

Raw benchmark rows for M3 Ultra (60-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
Qwen 2.5 14B	Q4_K - Medium	—	—	34.4 tok/s	444.6 tok/s	llamafile	ref

Models tested on this chip

Qwen 2.5 14B

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 →