Phi-3 Medium 14B Instruct on Apple M3 Pro (18GB Unified)
Apple M3 Pro (18GB Unified) can run Phi-3 Medium 14B Instruct at 6 tok/s at Q3_K_M, though performance is marginal. Consider a higher-end GPU for better results.
Model Size
14B
Device VRAM
18 GB
Bandwidth
150 GB/s
Quantizations Tested
1
Performance by Quantization
Each row shows Phi-3 Medium 14B Instruct performance at a different quality level on Apple M3 Pro (18GB Unified).
| Quantization | Speed | TTFT | Fits in VRAM | Rating | Confidence |
|---|---|---|---|---|---|
| Q3_K_M | 6 tok/s | 1400ms | ✓ Yes | Marginal | estimated |
Notes
Q3_K_M
Fits at Q3. Very slow at 150 GB/s. Marginal for reasoning tasks.
About Phi-3 Medium 14B Instruct
Phi-3 Medium 14B Instruct (14B) is a chat, coding, reasoning, multi-purpose model. 14B model with strong reasoning and coding performance. Fits comfortably on 16GB GPUs at Q4 and excels at structured output tasks. MIT license makes it attractive for commercial use.
View all Phi-3 Medium 14B Instruct hardware options →About Apple M3 Pro (18GB Unified)
Apple M3 Pro (18GB Unified) has 18 GB at 150 GB/s. Available in MacBook Pro 14", MacBook Pro 16".
See all models Apple M3 Pro (18GB Unified) can run →Source: MLX performance estimates (2026-03-15)
Data last updated: 2026-03-01