Microsoft on Apple M4
Can I run Phi-4 14B on an Mac Studio M4 Max 128GB?
Yes. Phi-4 14B at Q4_K_M uses 10.5 GB of the 96.0 GB available on a Mac Studio M4 Max 128GB, and runs at about 38.0 tokens per second. You can push the context to 16K.
Runs comfortably
10.5 GB of 96.0 GB · 11%096 GB
Weights
8.4 GB
KV cache
1.6 GB
Runtime overhead
0.5 GB
Phi-4 14B at Q4_K_M leaves 85.5 GB spare on a Mac Studio M4 Max 128GB. There is room to raise the context length or move up a quantisation level.
Generation38.0tok/s
Prompt processing486tok/s
Max context16Ktokens
KV per 1K tokens0GB
Every quantisation of Phi-4 14B on a Mac Studio M4 Max 128GB
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 | 12.4 |
| INT8 / W8A8 | 8.50 | 14.3 GB | 16.4 GB | Runs comfortably | 16K | 23.1 |
| Q8_0 (GGUF) | 8.50 | 14.3 GB | 16.4 GB | Runs comfortably | 16K | 23.1 |
| FP8 (E4M3) | 8.00 | 13.7 GB | 15.8 GB | Runs comfortably | 16K | 24.1 |
| Q6_K | 6.56 | 11.2 GB | 13.3 GB | Runs comfortably | 16K | 29.1 |
| Q5_K_M | 5.67 | 9.7 GB | 11.8 GB | Runs comfortably | 16K | 33.2 |
| Q5_K_S | 5.52 | 9.4 GB | 11.5 GB | Runs comfortably | 16K | 34.1 |
| AWQ 4-bit | 4.25 | 8.7 GB | 10.8 GB | Runs comfortably | 16K | 36.8 |
| GPTQ 4-bit | 4.25 | 8.7 GB | 10.8 GB | Runs comfortably | 16K | 36.8 |
| MXFP4 | 4.25 | 8.7 GB | 10.8 GB | Runs comfortably | 16K | 36.8 |
| Q4_K_M | 4.85 | 8.4 GB | 10.5 GB | Runs comfortably | 16K | 38.0 |
| Q4_K_S | 4.58 | 7.9 GB | 10.0 GB | Runs comfortably | 16K | 39.9 |
| Q4_0 | 4.55 | 7.9 GB | 10.0 GB | Runs comfortably | 16K | 40.1 |
| IQ4_XS | 4.25 | 7.4 GB | 9.5 GB | Runs comfortably | 16K | 42.4 |
| Q3_K_M | 3.91 | 6.9 GB | 9.0 GB | Runs comfortably | 16K | 45.3 |
| IQ3_M | 3.70 | 6.5 GB | 8.6 GB | Runs comfortably | 16K | 47.4 |
| IQ3_XXS | 3.06 | 5.5 GB | 7.6 GB | Runs comfortably | 16K | 54.9 |
| Q2_K | 2.63 | 4.8 GB | 6.9 GB | Runs comfortably | 16K | 61.5 |
| IQ2_XXS | 2.06 | 3.9 GB | 6.0 GB | Runs comfortably | 16K | 73.2 |
| IQ1_M | 1.75 | 3.4 GB | 5.5 GB | Runs comfortably | 16K | 81.5 |