can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA RTX 3050 Laptop (6GB) run LFM2.5 2.6B?

LFM · See model card · estimated for a 6.0 GB machine at 4K context.

Yes — it runs great.

Best fit: LFM2.5 2.6B at Q8_0 · 2.9 GB · 38–57 tok/s on a NVIDIA RTX 3050 Laptop (6GB).

Every quantization on this machine

QuantSizeSpeedFit
Q4_K_M1.7 GB60–90 tok/sRuns great
Q5_K_M1.9 GB53–79 tok/sRuns great
Q6_K2.2 GB47–71 tok/sRuns great
Q8_02.9 GB38–57 tok/sRuns great
FP165.4 GB21–32 tok/sWon't fit

Ran LFM2.5 2.6B on a NVIDIA RTX 3050 Laptop (6GB)? Add your real numbers →