can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA RTX 4060 Ti (8GB) run Granite 4.2 8B?

Granite · Apache 2.0 · estimated for a 8.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Granite 4.2 8B at Q3_K_M · 4.4 GB · 38–57 tok/s on a NVIDIA RTX 4060 Ti (8GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K3.4 GB46–68 tok/sRuns great
Q3_K_M4.4 GB38–57 tok/sRuns great
Q4_K_M5.4 GB32–48 tok/sTight / slow
Q5_K_M6.3 GB28–43 tok/sWon't fit
Q6_K7.2 GB25–38 tok/sWon't fit
Q8_09.4 GB20–30 tok/sWon't fit
FP1617.6 GB11–17 tok/sWon't fit

Ran Granite 4.2 8B on a NVIDIA RTX 4060 Ti (8GB)? Add your real numbers →