作者: Jakub Rusinowski · 最后更新: 2026年7月10日
Yes — the Llama 3.3 family runs on the Apple M4.
在亚马逊查看价格 — Apple Mac mini M4 (16GB)
| VRAM | 32 GB unified memory |
| Memory Bandwidth | 120 GB/s |
| Llama 3.3 70B Instruct | Q2_K_XS (Tight) · 26 GB · ~5 tok/s (est.) |
Yes — the Llama 3.3 family runs on the Apple M4.
Llama 3.3 70B Instruct at Q2_K_XS (Tight) quantization (26 GB), estimated ~5 tokens/sec.
← Can I Run It? | Llama 3.3 Model Page | Apple M4 GPU Page | Check Your Hardware