Can I run this LLM?
Can a NVIDIA GB300 Grace Blackwell (288GB HBM + 480GB) run Llama 3.3 70B Instruct?
Llama · Llama 3.3 Community · estimated for a 288.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Llama 3.3 70B Instruct at FP16 · 141.1 GB · 37–56 tok/s on a NVIDIA GB300 Grace Blackwell (288GB HBM + 480GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 26.4 GB | 135–202 tok/s | Runs great |
| Q3_K_M | 34.3 GB | 114–171 tok/s | Runs great |
| Q4_K_M | 42.5 GB | 99–148 tok/s | Runs great |
| Q5_K_M | 50.0 GB | 88–131 tok/s | Runs great |
| Q6_K | 57.9 GB | 78–118 tok/s | Runs great |
| Q8_0 | 75.0 GB | 64–96 tok/s | Runs great |
| FP16 | 141.1 GB | 37–56 tok/s | Runs great |
Open the full calculator →Everything a NVIDIA GB300 Grace Blackwell (288GB HBM + 480GB) runsLlama 3.3 70B Instruct on other machinesWhat to buy to run it →
Ran Llama 3.3 70B Instruct on a NVIDIA GB300 Grace Blackwell (288GB HBM + 480GB)? Add your real numbers →