can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA RTX 3060 Laptop (6GB) run Granite 4.2 8B?

Granite · Apache 2.0 · estimated for a 6.0 GB machine at 4K context.

Yes, but it's tight.

Best fit: Granite 4.2 8B at Q2_K · 3.4 GB · 52–78 tok/s on a NVIDIA RTX 3060 Laptop (6GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K3.4 GB52–78 tok/sTight / slow
Q3_K_M4.4 GB44–65 tok/sWon't fit
Q4_K_M5.4 GB37–56 tok/sWon't fit
Q5_K_M6.3 GB33–49 tok/sWon't fit
Q6_K7.2 GB29–43 tok/sWon't fit
Q8_09.4 GB23–35 tok/sWon't fit
FP1617.6 GB13–20 tok/sWon't fit

Ran Granite 4.2 8B on a NVIDIA RTX 3060 Laptop (6GB)? Add your real numbers →