can-i-run-this-llm

Can I run this LLM?

Can a AMD RX 7900 XTX (24GB) run LFM2.5 2.6B?

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

Yes — it runs great.

Best fit: LFM2.5 2.6B at FP16 · 5.4 GB · 96–144 tok/s on a AMD RX 7900 XTX (24GB).

Every quantization on this machine

QuantSizeSpeedFit
Q4_K_M1.7 GB193–290 tok/sRuns great
Q5_K_M1.9 GB180–270 tok/sRuns great
Q6_K2.2 GB168–252 tok/sRuns great
Q8_02.9 GB146–218 tok/sRuns great
FP165.4 GB96–144 tok/sRuns great

Ran LFM2.5 2.6B on a AMD RX 7900 XTX (24GB)? Add your real numbers →