M2 Ultra (GPU count not published, 128 GB) — benchmark record

M2 Ultra (GPU count not published, 128 GB) local LLM benchmarks on Apple Silicon Mac with 3 published rows across 2 models. Peak published speed is 120.4 tok/s on Llama 3.2 1B. Published runtimes include llamafile, MLX.

3Benchmark rows

2Models tested

120.4Fastest avg tok/s (llama-3-2-1b-instruct)

0Lab benchmarks

Quick take

Best published speed here is 120.4 tok/s on Llama 3.2 1B at Q4_K - Medium. This page is evidence, not the full buying answer.

Based on 3 external benchmarks; no lab runs yet.

Published runtimes: llamafile, MLX.

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 Llama 3.2 1B, Qwen3.5-27B. Published runtime coverage on this chip includes llamafile, MLX. Fastest published row is 120.4 tok/s on Llama 3.2 1B at Q4_K - Medium.

Llama 3.2 1B Qwen3.5-27B

Raw benchmark rows for M2 Ultra (GPU count not published, 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	Q4_K - Medium	—	—	120.4 tok/s	659.8 tok/s	llamafile	ref
Qwen3.5-27B	8bit	—	—	27.1 tok/s	—	MLX	ref
Qwen3.5-27B	8bit	—	—	20.6 tok/s	—	MLX	ref

Models tested on this chip

Llama 3.2 1B 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 →