can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA RTX 3060 (12GB) run Granite 4.2 8B?

Granite · Apache 2.0 · estimated for a 12.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Granite 4.2 8B at Q6_K · 7.2 GB · 31–46 tok/s on a NVIDIA RTX 3060 (12GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K3.4 GB55–83 tok/sRuns great
Q3_K_M4.4 GB46–69 tok/sRuns great
Q4_K_M5.4 GB39–59 tok/sRuns great
Q5_K_M6.3 GB35–52 tok/sRuns great
Q6_K7.2 GB31–46 tok/sRuns great
Q8_09.4 GB25–37 tok/sWon't fit
FP1617.6 GB14–21 tok/sWon't fit

Ran Granite 4.2 8B on a NVIDIA RTX 3060 (12GB)? Add your real numbers →