can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA RTX 4090 (24GB) run Granite 4.2 30B?

Granite · Apache 2.0 · estimated for a 24.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Granite 4.2 30B at Q3_K_M · 14.1 GB · 43–65 tok/s on a NVIDIA RTX 4090 (24GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K10.9 GB53–80 tok/sRuns great
Q3_K_M14.1 GB43–65 tok/sRuns great
Q4_K_M17.7 GB36–54 tok/sTight / slow
Q5_K_M20.8 GB31–47 tok/sWon't fit
Q6_K24.0 GB27–41 tok/sWon't fit
Q8_031.1 GB22–33 tok/sWon't fit
FP1658.6 GB12–18 tok/sWon't fit

Ran Granite 4.2 30B on a NVIDIA RTX 4090 (24GB)? Add your real numbers →