can-i-run-this-llm

Can I run this LLM?

Can a Intel Arc B580 (12GB) run LFM2.5 8B-A1B (MoE)?

LFM · See model card · estimated for a 12.0 GB machine at 4K context.

Yes — it runs great.

Best fit: LFM2.5 8B-A1B (MoE) at Q6_K · 7.0 GB · 153–230 tok/s on a Intel Arc B580 (12GB).

Every quantization on this machine

QuantSizeSpeedFit
Q4_K_M5.2 GB179–268 tok/sRuns great
Q5_K_M6.0 GB165–248 tok/sRuns great
Q6_K7.0 GB153–230 tok/sRuns great
Q8_09.0 GB131–197 tok/sTight / slow
FP1617.0 GB85–127 tok/sWon't fit

Ran LFM2.5 8B-A1B (MoE) on a Intel Arc B580 (12GB)? Add your real numbers →