can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA L40S (48GB) run LFM2.5 2.6B?

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

Yes — it runs great.

Best fit: LFM2.5 2.6B at FP16 · 5.4 GB · 89–133 tok/s on a NVIDIA L40S (48GB).

Every quantization on this machine

QuantSizeSpeedFit
Q4_K_M1.7 GB184–275 tok/sRuns great
Q5_K_M1.9 GB170–255 tok/sRuns great
Q6_K2.2 GB158–238 tok/sRuns great
Q8_02.9 GB136–205 tok/sRuns great
FP165.4 GB89–133 tok/sRuns great

Ran LFM2.5 2.6B on a NVIDIA L40S (48GB)? Add your real numbers →