Can Phi 3.5 vision instruct run on the Mac M4 Pro 24GB?
Yes. At 8K context the best fit is F16, using about 11.2 GB of the 16.1 GB usable on the Mac M4 Pro 24GB. Estimated speed ceiling: ~33 tokens/sec.
Memory by quant and context
| Quant | 4K ctx | 8K ctx | 32K ctx | 128K ctx | Max tok/s (est., 8K) |
|---|---|---|---|---|---|
| 2-bit (Q2_K) | 3.4 GB Fits | 4.9 GB Fits | 13.9 GB Fits | 49.9 GB No | 176 |
| 3-bit (Q3_K_M) | 3.8 GB Fits | 5.3 GB Fits | 14.3 GB Fits | 50.3 GB No | 135 |
| 4-bit (Q4_K_M) | 4.3 GB Fits | 5.8 GB Fits | 14.8 GB Tight | 50.8 GB No | 108 |
| 5-bit (Q5_K_M) | 4.7 GB Fits | 6.2 GB Fits | 15.2 GB Tight | 51.2 GB No | 92 |
| 6-bit (Q6_K) | 5.1 GB Fits | 6.6 GB Fits | 15.6 GB Tight | 51.6 GB No | 80 |
| 8-bit (Q8_0) | 6.1 GB Fits | 7.6 GB Fits | 16.6 GB No | 52.6 GB No | 62 |
| 16-bit (F16/BF16) | 9.7 GB Fits | 11.2 GB Fits | 20.2 GB No | 56.2 GB No | 33 |
• real GGUF file size. Speed is a bandwidth ceiling (273 GB/s), not a benchmark. Methodology.
More
Phi 3.5 vision instruct on every GPU and Mac · Every model that runs on the Mac M4 Pro 24GB · Apple Silicon guide · Try other settings in the calculator
Data: Hugging Face Hub (microsoft/Phi-3.5-vision-instruct), Apple specs. Data as of 2026-11-17.