作者: Jakub Rusinowski · 最后更新: 2026年7月10日
Yes — the Llama 3.3 family runs on the NVIDIA RTX 6000 Ada Generation.
在亚马逊查看价格 — NVIDIA RTX 6000 Ada Generation 48GB
| VRAM | 48 GB |
| Memory Bandwidth | 960 GB/s |
| Llama 3.3 70B Instruct | Q2_K_XS (Tight) · 26 GB · ~37 tok/s (est.) |
Yes — the Llama 3.3 family runs on the NVIDIA RTX 6000 Ada Generation.
Llama 3.3 70B Instruct at Q2_K_XS (Tight) quantization (26 GB), estimated ~37 tokens/sec.
← Can I Run It? | Llama 3.3 Model Page | NVIDIA RTX 6000 Ada Generation GPU Page | Check Your Hardware