Autor: Jakub Rusinowski · Ostatnia aktualizacja: 24 lutego 2026
Yes, comfortably — you'll have ~67 GB of headroom running Qwen 3.5 397B-A17B at IQ2_M (sub-Q4) (125 GB, ~149 tok/s (est.)).
Sprawdź cenę na Amazon — Apple Mac Studio M2 Ultra
| VRAM | 192 GB unified memory |
| Memory Bandwidth | 800 GB/s |
| Qwen 3.5 397B-A17B | IQ2_M (sub-Q4) · 125 GB · ~149 tok/s (est.) |
| Qwen 3.5 122B-A10B | Q4_K_M · 74 GB · ~132 tok/s (est.) |
| Qwen 3.5 35B-A3B | Q4_K_M · 21.4 GB · ~400 tok/s (est.) |
| Qwen 3.5 27B | Q4_K_M · 16.5 GB · ~48 tok/s (est.) |
| Qwen 3.5 9B | Q4_K_M · 6.6 GB · ~121 tok/s (est.) |
| Qwen 3.5 4B | Q4_K_M · 3.4 GB · ~235 tok/s (est.) |
| Qwen 3.5 2B | Q4_K_M · 2.7 GB · ~296 tok/s (est.) |
| Qwen 3.5 0.8B | Q4_K_M · 1 GB · ~400 tok/s (est.) |
At 2 hrs/day, buying (~$3,999) beats renting at $1.54/hr after about 3.6 years.
Affiliate links — we may earn a commission if you sign up, at no extra cost to you.
Cloud rates verified 2026-07 — estimates, and marketplace prices vary. Buying price is GPU MSRP only, not a full PC.
Yes, comfortably — you'll have ~67 GB of headroom running Qwen 3.5 397B-A17B at IQ2_M (sub-Q4) (125 GB, ~149 tok/s (est.)).
Qwen 3.5 397B-A17B at IQ2_M (sub-Q4) quantization (125 GB), estimated ~149 tokens/sec.
← Can I Run It? | Qwen 3.5 Model Page | Apple M2 Ultra GPU Page | Check Your Hardware