can-i-run-this-llm

Can I run this LLM?

Can a Intel Arc B580 (12GB) run Ornith 1.5 9B?

Ornith · MIT · estimated for a 12.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Ornith 1.5 9B at Q6_K · 7.7 GB · 38–58 tok/s on a Intel Arc B580 (12GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K4.1 GB66–99 tok/sRuns great
Q3_K_M4.9 GB56–85 tok/sRuns great
Q4_K_M5.9 GB48–73 tok/sRuns great
Q5_K_M6.9 GB43–64 tok/sRuns great
Q6_K7.7 GB38–58 tok/sRuns great
Q8_09.6 GB32–48 tok/sTight / slow
FP1617.9 GB18–27 tok/sWon't fit

Ran Ornith 1.5 9B on a Intel Arc B580 (12GB)? Add your real numbers →