can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA H100 SXM (80GB) run Granite 4.2 30B?

Granite · Apache 2.0 · estimated for a 80.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Granite 4.2 30B at FP16 · 58.6 GB · 37–56 tok/s on a NVIDIA H100 SXM (80GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K10.9 GB133–199 tok/sRuns great
Q3_K_M14.1 GB113–169 tok/sRuns great
Q4_K_M17.7 GB97–145 tok/sRuns great
Q5_K_M20.8 GB87–130 tok/sRuns great
Q6_K24.0 GB78–117 tok/sRuns great
Q8_031.1 GB64–95 tok/sRuns great
FP1658.6 GB37–56 tok/sRuns great

Ran Granite 4.2 30B on a NVIDIA H100 SXM (80GB)? Add your real numbers →