llamaperf

Gemma 4 5.1B E2B

on Unknown GPU · llama.cpp

Tone: mixed
May 1, 2026
Throughput
5-10 t/s gen
Quant
Q4 (GGUF)

Use cases

text-generation

Summary

User reports Gemma 4 E2B at 5-10 t/s on CPU. The run is CPU-only, with no GPU involved. User considers E2B usable in this CPU-only configuration.