Skip to content

Rig score · mac

Device readout 2026-10-05
Rig Score S tier
88%
Apple M4 Max (128GB) · 128 GB
runs 136 of 155 models · biggest Devstral 2 123B
localmodel.run/rig

Apple M4 Max (128GB)

Runs 136 of 155 models (88%)

Elite, runs the biggest open models, including 70B.

Biggest it can run: Devstral 2 123B

Grade
S
Runnable
136
Total
155
Coverage
88%

What Apple M4 Max (128GB) can run

At 128 GB of unified memory, Apple M4 Max (128GB) runs 136 of 155 tracked local models, 88% coverage that earns a S. The largest it handles is Devstral 2 123B at 123B parameters; anything bigger needs more memory or a lower quantization.

Apple Silicon shares one 128 GB pool between CPU and GPU, so almost all of it is available to a model. MLX and llama.cpp Metal builds give the best speed here; close memory-heavy apps before loading a large model.

135 run well 1 tight fit 19 too big

Top models on Apple M4 Max (128GB)

FAQ

What local AI rig score does Apple M4 Max (128GB) get?

Apple M4 Max (128GB) scores S: it runs 136 of 155 tracked local LLMs (88%). The biggest it can run is Devstral 2 123B.

How big a model can Apple M4 Max (128GB) run?

Apple M4 Max (128GB) runs models up to Devstral 2 123B (123B parameters) at Q4_K_M. Its memory is shared with the system, so leave a few GB for the OS.

Is Apple M4 Max (128GB) good for running local LLMs?

Apple Silicon shares one 128 GB pool between CPU and GPU, so almost all of it is available to a model. MLX and llama.cpp Metal builds give the best speed here; close memory-heavy apps before loading a large model.

Want your own? Check your rig on the homepage →

Score from coverage of 155 tracked models, estimated with our memory methodology.