can-i-run-this-llm

Can I run this LLM?

Can a AMD RX 7900 XTX (24GB) run Phi-4 14B?

Phi · MIT · estimated for a 24.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Phi-4 14B at Q8_0 · 15.6 GB · 39–58 tok/s on a AMD RX 7900 XTX (24GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K5.6 GB85–127 tok/sRuns great
Q3_K_M7.2 GB71–107 tok/sRuns great
Q4_K_M8.9 GB61–91 tok/sRuns great
Q5_K_M10.4 GB54–81 tok/sRuns great
Q6_K12.0 GB48–72 tok/sRuns great
Q8_015.6 GB39–58 tok/sRuns great
FP1629.3 GB22–33 tok/sWon't fit

Ran Phi-4 14B on a AMD RX 7900 XTX (24GB)? Add your real numbers →