can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA DGX Spark (GB10, 128GB) run Qwen3.8 Flash Next (MoE)?

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

Yes, but it's tight.

Best fit: Qwen3.8 Flash Next (MoE) at Q2_K · 80.9 GB · 47–70 tok/s on a NVIDIA DGX Spark (GB10, 128GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K80.9 GB47–70 tok/sTight / slow
Q3_K_M92.0 GB43–64 tok/sWon't fit
Q4_K_M119.6 GB35–53 tok/sWon't fit
Q5_K_M134.7 GB32–48 tok/sWon't fit
Q6_K168.1 GB27–40 tok/sWon't fit
Q8_0188.3 GB24–36 tok/sWon't fit
FP16354.0 GB14–21 tok/sWon't fit
Open the full calculator →Everything a NVIDIA DGX Spark (GB10, 128GB) runsQwen3.8 Flash Next (MoE) on other machinesWhat to buy to run it →

Ran Qwen3.8 Flash Next (MoE) on a NVIDIA DGX Spark (GB10, 128GB)? Add your real numbers →