MetaLlama 3.3 70B Instruct on NVIDIA RTX PRO 6000 Blackwell Max-Q
RTX PRO 6000 Blackwell Max-Q runs Llama 3.3 70B Instruct at Q8_0 — 13 tok/s. Usable on 96 GB VRAM — see full quantization options below.
Model Size
70.6B
Device VRAM
96 GB
Bandwidth
1800 GB/s
Quantization
Q8_0
Performance by Quantization
OwnRig currently has one published compatibility entry for Llama 3.3 70B Instruct on NVIDIA RTX PRO 6000 Blackwell Max-Q at Q8_0. This is the best supported pairing we can stand behind today.
| Quantization | Speed | TTFT | Fits in VRAM | Rating | Confidence |
|---|---|---|---|---|---|
| Q8_0 | 13 tok/s | 630ms | ✓ Yes | Acceptable | estimated |
Notes
Q8_0
96 GB GDDR7 fits Q8_0 (78 GB) with 18 GB headroom. 1.8 TB/s bandwidth. Near-FP16 quality — minimal quantization loss.
About Llama 3.3 70B Instruct
Llama 3.3 70B Instruct (70.6B) is a chat, coding, reasoning, multi-purpose model. Flagship Llama 3.3 model with best-in-class general and coding performance.
View all Llama 3.3 70B Instruct hardware options →About NVIDIA RTX PRO 6000 Blackwell Max-Q
NVIDIA RTX PRO 6000 Blackwell Max-Q has 96 GB at 1800 GB/s. Street price: $7,000.
See all models NVIDIA RTX PRO 6000 Blackwell Max-Q can run →Estimate method: Estimated from full RTX PRO 6000 with ~8% reduction for Max-Q 300W power envelope. Reference hardware source: nvidia.com (2026-03-29)
Performance varies by driver version, inference engine, quantization method, context length, and system configuration. Figures shown are estimates based on community benchmarks and may not reflect your exact setup. Product names are trademarks of their respective owners. OwnRig is independent and not affiliated with any hardware or AI model provider.