Skip to content
llm-speed

Phi-4 vs Gemma-2-9b-it

A single shareable card for the Phi-4 vs Gemma-2-9b-it matchup. Numbers are the best decode tok/s submitted on the llm-speed suite — every side links back to the run it came from.

Phi-4 vs Gemma-2-9b-it

Best decode tok/s across every rig submitted for each model.

Microsoft · 14B
141tok/s
decode (best submitted run)
source: r_e-k4aea8ipr
Google · 9B
153tok/s
decode (best submitted run)
source: r__b_bzmmab_8
Gemma-2-9b-it faster → +11.8 tok/s (1.08× faster)

Need the long-form table? Open the Phi-4 vs Gemma-2-9b-it comparison for every overlapping (model × hardware) row, source runs, and methodology.