Autor: Jakub Rusinowski · Ostatnia aktualizacja: 10 lipca 2026
Yes — the Llama 3.2 Family family runs on the NVIDIA RTX PRO 6000 Blackwell.
Sprawdź cenę na Amazon — NVIDIA RTX PRO 6000 Blackwell 96GB
| VRAM | 96 GB |
| Memory Bandwidth | 1792 GB/s |
| Llama 3.2 90B Vision Instruct | Q4_K_M · 54 GB · ~33 tok/s (est.) |
| Llama 3.2 11B Vision Instruct | Q4_K_M · 7.8 GB · ~230 tok/s (est.) |
| Llama 3.2 3B Instruct | Q4_K_M · 2.2 GB · ~400 tok/s (est.) |
| Llama 3.2 1B Instruct | Q4_K_M · 0.8 GB · ~400 tok/s (est.) |
Yes — the Llama 3.2 Family family runs on the NVIDIA RTX PRO 6000 Blackwell.
Llama 3.2 90B Vision Instruct at Q4_K_M quantization (54 GB), estimated ~33 tokens/sec.
← Can I Run It? | Llama 3.2 Family Model Page | NVIDIA RTX PRO 6000 Blackwell GPU Page | Check Your Hardware