can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA H100 SXM (80GB) run LFM2.5 8B-A1B (MoE)?

LFM · See model card · estimated for a 80.0 GB machine at 4K context.

Yes — it runs great.

Best fit: LFM2.5 8B-A1B (MoE) at FP16 · 17.0 GB · 253–379 tok/s on a NVIDIA H100 SXM (80GB).

Every quantization on this machine

QuantSizeSpeedFit
Q4_K_M5.2 GB321–482 tok/sRuns great
Q5_K_M6.0 GB315–472 tok/sRuns great
Q6_K7.0 GB308–462 tok/sRuns great
Q8_09.0 GB295–442 tok/sRuns great
FP1617.0 GB253–379 tok/sRuns great

Ran LFM2.5 8B-A1B (MoE) on a NVIDIA H100 SXM (80GB)? Add your real numbers →