Written by Jakub Rusinowski · Last updated July 10, 2026
Yes — the Llama 4 family runs on the Apple M2.
| VRAM | 24 GB unified memory |
| Memory Bandwidth | 100 GB/s |
| Llama 4 Scout 17B | Q4_K_M · 10.5 GB · ~61 tok/s (est.) |
Yes — the Llama 4 family runs on the Apple M2.
Llama 4 Scout 17B at Q4_K_M quantization (10.5 GB), estimated ~61 tokens/sec.
← Can I Run It? | Llama 4 Model Page | Apple M2 GPU Page | Check Your Hardware