Can I Run Llama 3.2 90B Vision Instruct on NVIDIA RTX PRO 6000 Blackwell?

Autor: Jakub Rusinowski · Ostatnia aktualizacja: 15 sierpnia 2026

Yes. Llama 3.2 90B Vision Instruct needs 53.6 GB at Q4_K_M and the NVIDIA RTX PRO 6000 Blackwell has 96 GB, leaving about 42.4 GB of headroom, at roughly 26 tok/s (estimated) with room for up to 64K of context.

The numbers

What to do next

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 90B Vision Instruct on this card:

Other Llama 3.2 Family sizes on the NVIDIA RTX PRO 6000 Blackwell

• Llama 3.2 11B Vision Instruct — runs (6.4 GB)
• Llama 3.2 3B Instruct — runs (1.9 GB)
• Llama 3.2 1B Instruct — runs (0.7 GB)

Llama 3.2 90B Vision Instruct on nearby hardware

• NVIDIA H100 80GB (80 GB) — runs
• Apple M4 Max (128 GB) — runs

All Llama 3.2 Family sizes on the NVIDIA RTX PRO 6000 Blackwell | VRAM calculator for Llama 3.2 90B Vision Instruct | NVIDIA RTX PRO 6000 Blackwell GPU page | Check your hardware