can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA H200 (141GB) run LFM2.5 1.2B?

LFM · See model card · estimated for a 141.0 GB machine at 4K context.

Yes — it runs great.

Best fit: LFM2.5 1.2B at FP16 · 2.3 GB · 294–441 tok/s on a NVIDIA H200 (141GB).

Every quantization on this machine

QuantSizeSpeedFit
Q4_K_M0.7 GB340–509 tok/sRuns great
Q5_K_M0.8 GB336–504 tok/sRuns great
Q6_K1.0 GB332–498 tok/sRuns great
Q8_01.3 GB323–485 tok/sRuns great
FP162.3 GB294–441 tok/sRuns great

Ran LFM2.5 1.2B on a NVIDIA H200 (141GB)? Add your real numbers →