can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA RTX 4070 Laptop (8GB) run Ornith 1.5 9B?

Ornith · MIT · estimated for a 8.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Ornith 1.5 9B at Q3_K_M · 4.9 GB · 34–51 tok/s on a NVIDIA RTX 4070 Laptop (8GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K4.1 GB40–60 tok/sRuns great
Q3_K_M4.9 GB34–51 tok/sRuns great
Q4_K_M5.9 GB29–43 tok/sTight / slow
Q5_K_M6.9 GB25–38 tok/sWon't fit
Q6_K7.7 GB23–34 tok/sWon't fit
Q8_09.6 GB19–28 tok/sWon't fit
FP1617.9 GB10–15 tok/sWon't fit

Ran Ornith 1.5 9B on a NVIDIA RTX 4070 Laptop (8GB)? Add your real numbers →