can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA H100 SXM (80GB) run Ling 3.0 Flash (MoE)?

Ling · MIT · estimated for a 80.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Ling 3.0 Flash (MoE) at Q3_K_M · 59.0 GB · 271–406 tok/s on a NVIDIA H100 SXM (80GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K45.9 GB287–430 tok/sRuns great
Q3_K_M59.0 GB271–406 tok/sRuns great
Q4_K_M77.8 GB250–375 tok/sWon't fit
Q5_K_M90.7 GB238–356 tok/sWon't fit
Q6_K109.3 GB222–333 tok/sWon't fit
Q8_0135.6 GB203–304 tok/sWon't fit
FP16255.1 GB146–219 tok/sWon't fit

Ran Ling 3.0 Flash (MoE) on a NVIDIA H100 SXM (80GB)? Add your real numbers →