can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA DGX Spark (GB10, 128GB) run Llama 4 Scout (MoE)?

Llama · See model card · estimated for a 128.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Llama 4 Scout (MoE) at Q5_K_M · 76.6 GB · 13–20 tok/s on a NVIDIA DGX Spark (GB10, 128GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K39.6 GB23–34 tok/sRuns great
Q3_K_M51.8 GB18–28 tok/sRuns great
Q4_K_M65.4 GB15–23 tok/sRuns great
Q5_K_M76.6 GB13–20 tok/sRuns great
Q6_K88.4 GB12–17 tok/sWon't fit
Q8_0114.5 GB9–14 tok/sWon't fit
FP16215.6 GB5–8 tok/sWon't fit

Ran Llama 4 Scout (MoE) on a NVIDIA DGX Spark (GB10, 128GB)? Add your real numbers →