Rig score · mac
Apple M4 Max (64GB)
Runs 126 of 155 models (81%)
Elite, runs the biggest open models, including 70B.
Biggest it can run: Qwen3-Coder-Next 80B-A3B
- Grade
- S
- Runnable
- 126
- Total
- 155
- Coverage
- 81%
What Apple M4 Max (64GB) can run
At 64 GB of unified memory, Apple M4 Max (64GB) runs 126 of 155 tracked local models, 81% coverage that earns a S. The largest it handles is Qwen3-Coder-Next 80B-A3B at 80B parameters; anything bigger needs more memory or a lower quantization.
Apple Silicon shares one 64 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 Max (64GB)
FAQ
What local AI rig score does Apple M4 Max (64GB) get?
Apple M4 Max (64GB) scores S: it runs 126 of 155 tracked local LLMs (81%). The biggest it can run is Qwen3-Coder-Next 80B-A3B.
How big a model can Apple M4 Max (64GB) run?
Apple M4 Max (64GB) runs models up to Qwen3-Coder-Next 80B-A3B (80B parameters) at Q4_K_M. Its memory is shared with the system, so leave a few GB for the OS.
Is Apple M4 Max (64GB) good for running local LLMs?
Apple Silicon shares one 64 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.