Rig score · mac
Apple M4 (24GB)
Runs 73 of 135 models (54%)
Strong, runs mid-size models up to ~14B.
Biggest it can run: Mistral Small 3.1 24B
- Grade
- B
- Runnable
- 73
- Total
- 135
- Coverage
- 54%
What Apple M4 (24GB) can run
At 24 GB of unified memory, Apple M4 (24GB) runs 73 of 135 tracked local models, 54% coverage that earns a B. The largest it handles is Mistral Small 3.1 24B at 24B parameters; anything bigger needs more memory or a lower quantization.
Apple Silicon shares one 24 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.
Top models on Apple M4 (24GB)
FAQ
What local AI rig score does Apple M4 (24GB) get?
Apple M4 (24GB) scores B: it runs 73 of 135 tracked local LLMs (54%). The biggest it can run is Mistral Small 3.1 24B.
How big a model can Apple M4 (24GB) run?
Apple M4 (24GB) runs models up to Mistral Small 3.1 24B (24B parameters) at Q4_K_M. Its memory is shared with the system, so leave a few GB for the OS.
Is Apple M4 (24GB) good for running local LLMs?
Apple Silicon shares one 24 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 135 tracked models, estimated with our memory methodology.