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 individual submitted decode results; each available side shows its source configuration. These are not repeated controlled comparisons.

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

Individual submitted decode results; hardware and workload shown below.

14B
140.9tok/s
decode (individual submitted result)
Model
phi-4
Reported hardware
RTX 5090 (32GB) + AMD Ryzen 7 9850X3D 8-Core Processor (8c) + 3…
Workload / suite
chat-short · suite-v1
Runtime
llama.cpp · version not reported
Quantization field
Not reported
Submitted
2026-07-01
source: r_e-k4aea8ipr
9B
152.7tok/s
decode (individual submitted result)
Model
gemma-2-9b-it
Reported hardware
RTX 5090 (32GB) + AMD Ryzen 7 9850X3D 8-Core Processor (8c) + 3…
Workload / suite
chat-short · suite-v1
Runtime
llama.cpp · version not reported
Quantization field
Not reported
Submitted
2026-07-01
source: r__b_bzmmab_8
These independently selected results can use different models, workloads and settings. They do not establish a hardware or model winner.

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.