00:02
2026-10-09
dev.to
large-language-models
Benchmarking Gemma 4 E2B on CPU with llama.cpp: A Practical Local AI Experiment
A developer benchmarked Gemma 4 E2B (QAT Q4_K_XL GGUF) running CPU-only via llama.cpp's llama-server on a resource-constrained AMD Athlon 3000G machine with 2 cores and 4 threads under WSL, measuring …