Microsoft on Apple M4
Can I run Phi-4 14B on an Mac Mini M4 Pro 48GB?
Yes. Phi-4 14B at Q4_K_M uses 10.5 GB of the 36.0 GB available on a Mac Mini M4 Pro 48GB, and runs at about 19.1 tokens per second. You can push the context to 16K.
Runs comfortably
10.5 GB of 36.0 GB · 29%036 GB
Weights
8.4 GB
KV cache
1.6 GB
Runtime overhead
0.5 GB
Phi-4 14B at Q4_K_M leaves 25.5 GB spare on a Mac Mini M4 Pro 48GB. There is room to raise the context length or move up a quantisation level.
Generation19.1tok/s
Prompt processing243tok/s
Max context16Ktokens
KV per 1K tokens0GB
Every quantisation of Phi-4 14B on a Mac Mini M4 Pro 48GB
Highlighted row is the highest quality that still fits at 8K context.
| Quantisation | bpw | Weights | Total | Verdict | Max ctx | tok/s |
|---|---|---|---|---|---|---|
| FP16 / BF16 | 16.00 | 27.4 GB | 29.5 GB | Runs comfortably | 16K | 6.23 |
| INT8 / W8A8 | 8.50 | 14.3 GB | 16.4 GB | Runs comfortably | 16K | 11.6 |
| Q8_0 (GGUF) | 8.50 | 14.3 GB | 16.4 GB | Runs comfortably | 16K | 11.6 |
| FP8 (E4M3) | 8.00 | 13.7 GB | 15.8 GB | Runs comfortably | 16K | 12.1 |
| Q6_K | 6.56 | 11.2 GB | 13.3 GB | Runs comfortably | 16K | 14.6 |
| Q5_K_M | 5.67 | 9.7 GB | 11.8 GB | Runs comfortably | 16K | 16.7 |
| Q5_K_S | 5.52 | 9.4 GB | 11.5 GB | Runs comfortably | 16K | 17.1 |
| AWQ 4-bit | 4.25 | 8.7 GB | 10.8 GB | Runs comfortably | 16K | 18.5 |
| GPTQ 4-bit | 4.25 | 8.7 GB | 10.8 GB | Runs comfortably | 16K | 18.5 |
| MXFP4 | 4.25 | 8.7 GB | 10.8 GB | Runs comfortably | 16K | 18.5 |
| Q4_K_M | 4.85 | 8.4 GB | 10.5 GB | Runs comfortably | 16K | 19.1 |
| Q4_K_S | 4.58 | 7.9 GB | 10.0 GB | Runs comfortably | 16K | 20.0 |
| Q4_0 | 4.55 | 7.9 GB | 10.0 GB | Runs comfortably | 16K | 20.1 |
| IQ4_XS | 4.25 | 7.4 GB | 9.5 GB | Runs comfortably | 16K | 21.3 |
| Q3_K_M | 3.91 | 6.9 GB | 9.0 GB | Runs comfortably | 16K | 22.8 |
| IQ3_M | 3.70 | 6.5 GB | 8.6 GB | Runs comfortably | 16K | 23.8 |
| IQ3_XXS | 3.06 | 5.5 GB | 7.6 GB | Runs comfortably | 16K | 27.7 |
| Q2_K | 2.63 | 4.8 GB | 6.9 GB | Runs comfortably | 16K | 31.0 |
| IQ2_XXS | 2.06 | 3.9 GB | 6.0 GB | Runs comfortably | 16K | 36.9 |
| IQ1_M | 1.75 | 3.4 GB | 5.5 GB | Runs comfortably | 16K | 41.2 |