Apple M4, 16 GB · Phi-4 · Q4_K_M
Tight. Phi-4 at Q4_K_M loads on Apple M4, 16 GB at 8,192 tokens and uses most of the fast memory, roughly 6–11 tokens per second.
| Piece | Value | Note |
|---|---|---|
| Weights | 8.43 GiB | phi-4-Q4_K_M.gguf |
| KV cache | 1.56 GiB | 8,192 tokens |
| Engine overhead | 0.50 GiB | Flat 0.5 GiB allowance |
| 5% headroom | 0.52 GiB | On the sum above |
| Total | 11.0 GiB | Tight |
| Fast memory | 12.0 GiB | After OS reserve |
| Speed | 6–11 tok/s | Dense bandwidth range |
ollama run phi4:14b
Apple M4, 16 GB · Phi-4 ·GGUF file · Methodology
FAQ
How was this fit calculated?
Weights 8.43 GiB, KV cache 1.56 GiB at 8,192 tokens, engine overhead 0.50 GiB, then 5% headroom, for 11.0 GiB. Fast memory available is 12.0 GiB.
What if I change the quant or the context?
This page is Q4_K_M at 8,192 tokens. A smaller quant or a shorter context lowers the total. The homepage calculator changes both without a new page.
Can I trust the tokens per second?
The range 6–11 tok/s is a bandwidth roofline, 55% to 80% efficient. This dense model reads the whole weight file each token. Measure your own box before you buy around it.
What do I type?
ollama run phi4:14b
Is Apple M4, 16 GB assumed to have extra RAM?
No separate RAM pool. The chip's unified memory is the whole budget, minus the OS reserve described on the methodology page.