can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA RTX 4090 (24GB) run LFM2.5 1.2B?

LFM · See model card · estimated for a 24.0 GB machine at 4K context.

Yes — it runs great.

Best fit: LFM2.5 1.2B at FP16 · 2.3 GB · 168–253 tok/s on a NVIDIA RTX 4090 (24GB).

Every quantization on this machine

QuantSizeSpeedFit
Q4_K_M0.7 GB265–398 tok/sRuns great
Q5_K_M0.8 GB255–383 tok/sRuns great
Q6_K1.0 GB245–367 tok/sRuns great
Q8_01.3 GB224–335 tok/sRuns great
FP162.3 GB168–253 tok/sRuns great

Ran LFM2.5 1.2B on a NVIDIA RTX 4090 (24GB)? Add your real numbers →