Autor: Jakub Rusinowski · Ostatnia aktualizacja: 15 sierpnia 2026
Yes. Llama 3.2 Vision 90B needs 53.6 GB at Q4_K_M and the Apple M1 Ultra has 128 GB, leaving about 74.4 GB of headroom, at roughly 8 tok/s (estimated) with room for up to 128K of context.
| Model | Llama 3.2 Vision 90B |
| Parameters | 90B |
| Quantization | Q4_K_M |
| VRAM needed | 53.6 GB |
| Apple M1 Ultra VRAM | 128 GB |
| Verdict | Runs |
| Max context | 128K |
| Estimated speed | ~8 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 Llama 3.2 Vision 90B 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 Llama 3.2 Vision sizes on the Apple M1 Ultra | VRAM calculator for Llama 3.2 Vision 90B | Apple M1 Ultra GPU page | Check your hardware