Apple M1 Ultra for local LLMs

5 measured results from 2 builds, each linked to its source.

Can it run? gpt-oss 20B on Apple M1 Ultra

All builds with the Apple M1 Ultra

All measured results

Hide speculative-decoding results ⚡ (MTP, DFlash, DSpark and similar draft-and-verify methods give much higher tok/s on predictable text and are not comparable 1:1 with plain decode)

All Apple M1 Ultra builds: see also all GPUs · best LLMs by memory size · download the dataset.

FAQ

How fast is the Apple M1 Ultra for local LLMs?

The fastest plain-decode result we have is 127.6 tok/s on Llama 3.2 3B (, llama.cpp) in Mac Studio M1 Ultra (64-core GPU) 128GB. Speed depends heavily on the model, quant and engine, so compare like with like in the table. RigBase lists 5 measured results from 2 builds.

How much memory does the Apple M1 Ultra have?

unified memory.

Which models have been measured on the Apple M1 Ultra?

DeepSeek R1 Distill 14B, Llama 3.1 70B, Llama 3.1 8B, Llama 3.2 3B, gpt-oss 20B.

Where do these numbers come from?

Every row links to a build page with its original public source (benchmark logs, READMEs, forum posts). RigBase does not re-run the benchmarks. Results marked ⚡ use speculative decoding and are not comparable 1:1 with plain decode.