can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA RTX 5090 (32GB) run Llama 3.3 70B Instruct?

Llama · Llama 3.3 Community · estimated for a 32.0 GB machine at 4K context.

Yes, but it's tight.

Best fit: Llama 3.3 70B Instruct at Q2_K · 26.4 GB · 42–63 tok/s on a NVIDIA RTX 5090 (32GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K26.4 GB42–63 tok/sTight / slow
Q3_K_M34.3 GB34–51 tok/sWon't fit
Q4_K_M42.5 GB28–42 tok/sWon't fit
Q5_K_M50.0 GB24–36 tok/sWon't fit
Q6_K57.9 GB21–32 tok/sWon't fit
Q8_075.0 GB17–25 tok/sWon't fit
FP16141.1 GB9–14 tok/sWon't fit
Open the full calculator →Everything a NVIDIA RTX 5090 (32GB) runsLlama 3.3 70B Instruct on other machinesWhat to buy to run it →

Ran Llama 3.3 70B Instruct on a NVIDIA RTX 5090 (32GB)? Add your real numbers →