can-i-run-this-llm

Can I run this LLM?

Can a Mac Studio M1 Ultra (64GB) run LFM2.5 1.2B?

LFM · See model card · estimated for a 64.0 GB machine at 4K context.

Yes — it runs great.

Best fit: LFM2.5 1.2B at FP16 · 2.3 GB · 98–146 tok/s on a Mac Studio M1 Ultra (64GB).

Every quantization on this machine

QuantSizeSpeedFit
Q4_K_M0.7 GB138–206 tok/sRuns great
Q5_K_M0.8 GB134–201 tok/sRuns great
Q6_K1.0 GB130–195 tok/sRuns great
Q8_01.3 GB121–182 tok/sRuns great
FP162.3 GB98–146 tok/sRuns great

Ran LFM2.5 1.2B on a Mac Studio M1 Ultra (64GB)? Add your real numbers →