can-i-run-this-llm

Can I run this LLM?

Can a Desktop CPU, DDR5 dual-channel (32GB) run Granite 4.2 30B?

Granite · Apache 2.0 · estimated for a 32.0 GB machine at 4K context.

Yes, but it's tight.

Best fit: Granite 4.2 30B at Q2_K · 10.9 GB · 3–4 tok/s on a Desktop CPU, DDR5 dual-channel (32GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K10.9 GB3–4 tok/sTight / slow
Q3_K_M14.1 GB2–3 tok/sTight / slow
Q4_K_M17.7 GB2–3 tok/sTight / slow
Q5_K_M20.8 GB1–2 tok/sTight / slow
Q6_K24.0 GB1–2 tok/sWon't fit
Q8_031.1 GB1–1 tok/sWon't fit
FP1658.6 GB1–1 tok/sWon't fit

Ran Granite 4.2 30B on a Desktop CPU, DDR5 dual-channel (32GB)? Add your real numbers →