can-i-run-this-llm

Can I run this LLM?

Can a MacBook Air/Pro M4 (16GB) run Ornith 1.5 9B?

Ornith · MIT · estimated for a 16.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Ornith 1.5 9B at Q4_K_M · 5.9 GB · 12–19 tok/s on a MacBook Air/Pro M4 (16GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K4.1 GB17–26 tok/sRuns great
Q3_K_M4.9 GB15–22 tok/sRuns great
Q4_K_M5.9 GB12–19 tok/sRuns great
Q5_K_M6.9 GB11–16 tok/sTight / slow
Q6_K7.7 GB10–15 tok/sTight / slow
Q8_09.6 GB8–12 tok/sTight / slow
FP1617.9 GB4–7 tok/sWon't fit

Ran Ornith 1.5 9B on a MacBook Air/Pro M4 (16GB)? Add your real numbers →