can-i-run-this-llm

Can I run this LLM?

Can a Mac Studio M3 Ultra (512GB) run LFM2.5 2.6B?

LFM · See model card · estimated for a 512.0 GB machine at 4K context.

Yes — it runs great.

Best fit: LFM2.5 2.6B at FP16 · 5.4 GB · 64–95 tok/s on a Mac Studio M3 Ultra (512GB).

Every quantization on this machine

QuantSizeSpeedFit
Q4_K_M1.7 GB111–167 tok/sRuns great
Q5_K_M1.9 GB106–159 tok/sRuns great
Q6_K2.2 GB100–151 tok/sRuns great
Q8_02.9 GB90–135 tok/sRuns great
FP165.4 GB64–95 tok/sRuns great

Ran LFM2.5 2.6B on a Mac Studio M3 Ultra (512GB)? Add your real numbers →