can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA A100 (80GB) run Phi-4 14B?

Phi · MIT · estimated for a 80.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Phi-4 14B at FP16 · 29.3 GB · 44–66 tok/s on a NVIDIA A100 (80GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K5.6 GB143–214 tok/sRuns great
Q3_K_M7.2 GB124–186 tok/sRuns great
Q4_K_M8.9 GB109–163 tok/sRuns great
Q5_K_M10.4 GB98–147 tok/sRuns great
Q6_K12.0 GB89–133 tok/sRuns great
Q8_015.6 GB73–110 tok/sRuns great
FP1629.3 GB44–66 tok/sRuns great

Ran Phi-4 14B on a NVIDIA A100 (80GB)? Add your real numbers →