Written by Jakub Rusinowski · Last updated August 15, 2026
Yes. Qwen 3.5 122B-A10B needs 73.7 GB at Q4_K_M and the Apple M2 Ultra has 192 GB, leaving about 118.3 GB of headroom, at roughly 50 tok/s (estimated) with room for up to 128K of context.
| Model | Qwen 3.5 122B-A10B |
| Parameters | 122B (10B active) |
| Quantization | Q4_K_M |
| VRAM needed | 73.7 GB |
| Apple M2 Ultra VRAM | 192 GB |
| Verdict | Runs |
| Max context | 128K |
| Estimated speed | ~50 tok/s |
Nothing to change — run it at Q4_K_M. If you want more capability, check whether the next size up also fits.
Running Qwen 3.5 122B-A10B on this card:
At 2 hrs/day, buying (~$3,999) beats renting at $0.77/hr after about 7.2 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.
All Qwen 3.5 sizes on the Apple M2 Ultra | VRAM calculator for Qwen 3.5 122B-A10B | Apple M2 Ultra GPU page | Check your hardware