can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA RTX 3080 (10GB) run Granite 4.2 8B?

Granite · Apache 2.0 · estimated for a 10.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Granite 4.2 8B at Q5_K_M · 6.3 GB · 66–100 tok/s on a NVIDIA RTX 3080 (10GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K3.4 GB100–150 tok/sRuns great
Q3_K_M4.4 GB86–129 tok/sRuns great
Q4_K_M5.4 GB74–111 tok/sRuns great
Q5_K_M6.3 GB66–100 tok/sRuns great
Q6_K7.2 GB60–89 tok/sTight / slow
Q8_09.4 GB49–73 tok/sWon't fit
FP1617.6 GB28–43 tok/sWon't fit

Ran Granite 4.2 8B on a NVIDIA RTX 3080 (10GB)? Add your real numbers →