can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA L40S (48GB) run LFM2.5 8B-A1B (MoE)?

LFM · See model card · estimated for a 48.0 GB machine at 4K context.

Yes — it runs great.

Best fit: LFM2.5 8B-A1B (MoE) at FP16 · 17.0 GB · 133–200 tok/s on a NVIDIA L40S (48GB).

Every quantization on this machine

QuantSizeSpeedFit
Q4_K_M5.2 GB236–354 tok/sRuns great
Q5_K_M6.0 GB223–335 tok/sRuns great
Q6_K7.0 GB211–317 tok/sRuns great
Q8_09.0 GB189–283 tok/sRuns great
FP1617.0 GB133–200 tok/sRuns great

Ran LFM2.5 8B-A1B (MoE) on a NVIDIA L40S (48GB)? Add your real numbers →