Rig score · mac
Apple M1 (8GB)
Runs 37 of 135 models (27%)
Entry, small 1-4B models only.
Biggest it can run: Gemma 4 E2B
- Grade
- D
- Runnable
- 37
- Total
- 135
- Coverage
- 27%
What Apple M1 (8GB) can run
At 8 GB of unified memory, Apple M1 (8GB) runs 37 of 135 tracked local models, 27% coverage that earns a D. The largest it handles is Gemma 4 E2B at 5.1B parameters; anything bigger needs more memory or a lower quantization.
Apple Silicon shares one 8 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 M1 (8GB)
FAQ
What local AI rig score does Apple M1 (8GB) get?
Apple M1 (8GB) scores D: it runs 37 of 135 tracked local LLMs (27%). The biggest it can run is Gemma 4 E2B.
How big a model can Apple M1 (8GB) run?
Apple M1 (8GB) runs models up to Gemma 4 E2B (5.1B parameters) at Q4_K_M. Its memory is shared with the system, so leave a few GB for the OS.
Is Apple M1 (8GB) good for running local LLMs?
Apple Silicon shares one 8 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.