作者: Jakub Rusinowski · 最后更新: 2026年7月10日
Yes — the Llama 4 family runs on the Apple M5.
| VRAM | 32 GB unified memory |
| Memory Bandwidth | 153 GB/s |
| Llama 4 Maverick 17B | Q4_K_M · 24 GB · ~150 tok/s (est.) |
| Llama 4 Scout 17B | Q4_K_M · 10.5 GB · ~93 tok/s (est.) |
Yes — the Llama 4 family runs on the Apple M5.
Llama 4 Maverick 17B at Q4_K_M quantization (24 GB), estimated ~150 tokens/sec.
← Can I Run It? | Llama 4 Model Page | Apple M5 GPU Page | Check Your Hardware