can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA GB300 Grace Blackwell (288GB HBM + 480GB) run Ling 3.0 Flash (MoE)?

Ling · MIT · estimated for a 288.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Ling 3.0 Flash (MoE) at FP16 · 255.1 GB · 224–336 tok/s on a NVIDIA GB300 Grace Blackwell (288GB HBM + 480GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K45.9 GB329–493 tok/sRuns great
Q3_K_M59.0 GB319–479 tok/sRuns great
Q4_K_M77.8 GB307–460 tok/sRuns great
Q5_K_M90.7 GB299–448 tok/sRuns great
Q6_K109.3 GB288–432 tok/sRuns great
Q8_0135.6 GB274–411 tok/sRuns great
FP16255.1 GB224–336 tok/sRuns great

Ran Ling 3.0 Flash (MoE) on a NVIDIA GB300 Grace Blackwell (288GB HBM + 480GB)? Add your real numbers →