can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA RTX 3090 (24GB) run LFM2.5 8B-A1B (MoE)?

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

Yes — it runs great.

Best fit: LFM2.5 8B-A1B (MoE) at FP16 · 17.0 GB · 140–210 tok/s on a NVIDIA RTX 3090 (24GB).

Every quantization on this machine

QuantSizeSpeedFit
Q4_K_M5.2 GB243–364 tok/sRuns great
Q5_K_M6.0 GB230–345 tok/sRuns great
Q6_K7.0 GB218–327 tok/sRuns great
Q8_09.0 GB196–294 tok/sRuns great
FP1617.0 GB140–210 tok/sRuns great

Ran LFM2.5 8B-A1B (MoE) on a NVIDIA RTX 3090 (24GB)? Add your real numbers →