can-i-run-this-llm

Can I run this LLM?

Can a Mac Studio M3 Ultra (96GB) run LFM2.5 1.2B?

LFM · See model card · estimated for a 96.0 GB machine at 4K context.

Yes — it runs great.

Best fit: LFM2.5 1.2B at FP16 · 2.3 GB · 98–148 tok/s on a Mac Studio M3 Ultra (96GB).

Every quantization on this machine

QuantSizeSpeedFit
Q4_K_M0.7 GB138–207 tok/sRuns great
Q5_K_M0.8 GB134–202 tok/sRuns great
Q6_K1.0 GB131–196 tok/sRuns great
Q8_01.3 GB122–183 tok/sRuns great
FP162.3 GB98–148 tok/sRuns great

Ran LFM2.5 1.2B on a Mac Studio M3 Ultra (96GB)? Add your real numbers →