MetaLlama 3.3 70B Instruct on NVIDIA Grace Blackwell Ultra GB300
Yes — Grace Blackwell Ultra GB300 runs Llama 3.3 70B Instruct excellently at Q8_0 — 55 tok/s. 288 GB VRAM with plenty of headroom.
Model Size
70.6B
Device VRAM
288 GB
Bandwidth
8000 GB/s
Quantization
Q8_0
Performance by Quantization
OwnRig currently has one published compatibility entry for Llama 3.3 70B Instruct on NVIDIA Grace Blackwell Ultra GB300 at Q8_0. This is the best supported pairing we can stand behind today.
| Quantization | Speed | TTFT | Fits in VRAM | Rating | Confidence |
|---|---|---|---|---|---|
| Q8_0 | 55 tok/s | 150ms | ✓ Yes | Excellent | estimated |
Notes
Q8_0
Full Q8 quality 70B flagship. 210GB headroom — can run with massive context.
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 Grace Blackwell Ultra GB300
NVIDIA Grace Blackwell Ultra GB300 has 288 GB at 8000 GB/s. Street price: $30,000.
See all models NVIDIA Grace Blackwell Ultra GB300 can run →Estimate method: Estimated from GB300 bandwidth ratio vs RTX 4090. Reference hardware source: dell.com (2026-03-23)
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.