can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA DGX Spark (GB10, 128GB) run LFM2.5 1.2B?

LFM · See model card · estimated for a 128.0 GB machine at 4K context.

Yes — it runs great.

Best fit: LFM2.5 1.2B at FP16 · 2.3 GB · 53–80 tok/s on a NVIDIA DGX Spark (GB10, 128GB).

Every quantization on this machine

QuantSizeSpeedFit
Q4_K_M0.7 GB99–149 tok/sRuns great
Q5_K_M0.8 GB94–141 tok/sRuns great
Q6_K1.0 GB88–133 tok/sRuns great
Q8_01.3 GB78–116 tok/sRuns great
FP162.3 GB53–80 tok/sRuns great

Ran LFM2.5 1.2B on a NVIDIA DGX Spark (GB10, 128GB)? Add your real numbers →