can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA DGX Spark (GB10, 128GB) run Ling 3.0 Flash (MoE)?

Ling · MIT · estimated for a 128.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Ling 3.0 Flash (MoE) at Q4_K_M · 77.8 GB · 44–65 tok/s on a NVIDIA DGX Spark (GB10, 128GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K45.9 GB62–93 tok/sRuns great
Q3_K_M59.0 GB53–79 tok/sRuns great
Q4_K_M77.8 GB44–65 tok/sRuns great
Q5_K_M90.7 GB39–58 tok/sWon't fit
Q6_K109.3 GB34–50 tok/sWon't fit
Q8_0135.6 GB28–42 tok/sWon't fit
FP16255.1 GB16–24 tok/sWon't fit

Ran Ling 3.0 Flash (MoE) on a NVIDIA DGX Spark (GB10, 128GB)? Add your real numbers →