can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA RTX 4080 (16GB) run LFM2.5 8B-A1B (MoE)?

LFM · See model card · estimated for a 16.0 GB machine at 4K context.

Yes — it runs great.

Best fit: LFM2.5 8B-A1B (MoE) at Q8_0 · 9.0 GB · 171–257 tok/s on a NVIDIA RTX 4080 (16GB).

Every quantization on this machine

QuantSizeSpeedFit
Q4_K_M5.2 GB220–330 tok/sRuns great
Q5_K_M6.0 GB207–310 tok/sRuns great
Q6_K7.0 GB194–291 tok/sRuns great
Q8_09.0 GB171–257 tok/sRuns great
FP1617.0 GB118–177 tok/sWon't fit

Ran LFM2.5 8B-A1B (MoE) on a NVIDIA RTX 4080 (16GB)? Add your real numbers →