can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA RTX Pro 6000 Blackwell (96GB) run Llama 4 Scout (MoE)?

Llama · See model card · estimated for a 96.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Llama 4 Scout (MoE) at Q4_K_M · 65.4 GB · 90–135 tok/s on a NVIDIA RTX Pro 6000 Blackwell (96GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K39.6 GB124–186 tok/sRuns great
Q3_K_M51.8 GB105–158 tok/sRuns great
Q4_K_M65.4 GB90–135 tok/sRuns great
Q5_K_M76.6 GB80–120 tok/sTight / slow
Q6_K88.4 GB72–108 tok/sWon't fit
Q8_0114.5 GB59–88 tok/sWon't fit
FP16215.6 GB34–52 tok/sWon't fit

Ran Llama 4 Scout (MoE) on a NVIDIA RTX Pro 6000 Blackwell (96GB)? Add your real numbers →