APPLE SILICON GUIDE
Apple Silicon unified memory for local LLMs
Apple Silicon does not expose a conventional dedicated VRAM number: CPU and GPU share the memory pool. The useful input is the memory assigned to the machine and the bandwidth available to the GPU.
Unified memory changes the question
A machine can use one pool for the operating system, CPU, and GPU. Leave headroom for macOS and other applications instead of treating the printed capacity as fully available to the model.
Capacity and bandwidth are separate
A larger unified-memory configuration can hold a larger model, but bandwidth still influences decode speed. The catalog keeps both values visible so they are not confused.
Test the backend with the workload
Metal is the hardware backend in the catalog, while MLX is one of the supported runtime command paths. Recheck the fit when you change context or quantization.
Apple Silicon entries in the catalog
| Machine | Unified memory | Bandwidth | Backend |
|---|---|---|---|
| MacBook Neo A18 Pro 8GB | 8 GB | 60 GB/s | metal |
| MacBook Pro M1 Max 32GB | 32 GB | 400 GB/s | metal |
| Mac mini M4 32GB | 32 GB | 120 GB/s | metal |
| MacBook Pro M1 Max 64GB | 64 GB | 400 GB/s | metal |
| Mac mini M4 Pro 64GB | 64 GB | 273 GB/s | metal |
| Mac Studio M3 Ultra 96GB | 96 GB | 819 GB/s | metal |
| MacBook Pro M4 Max 128GB | 128 GB | 546 GB/s | metal |
| Mac Studio M2 Ultra 192GB | 192 GB | 800 GB/s | metal |
Memory and bandwidth are catalog inputs. Actual usable memory and speed vary with system allocation, backend, thermals, and workload.
Ready to test your machine?
Enter a GPU or usable VRAM and the calculator will rank models for your workload, quantization, and context.
Open the calculator