Written by Jakub Rusinowski · Last updated June 15, 2026
Yes — the GPT-oss 120B family runs on the Apple M4 Max.
| VRAM | 128 GB unified memory |
| Memory Bandwidth | 546 GB/s |
| GPT-oss 120B | Q4_K_M · 65 GB · ~8 tok/s (est.) |
Yes — the GPT-oss 120B family runs on the Apple M4 Max.
GPT-oss 120B at Q4_K_M quantization (65 GB), estimated ~8 tokens/sec.
← Can I Run It? | GPT-oss 120B Model Page | Apple M4 Max GPU Page | Check Your Hardware