AI article
A 4 GB Laptop GPU Beats a 12-Core CPU by 4.3x on Gemma 4
Community description: Serving Gemma 4 E2B q4_0 through llama.cpp on one laptop, twice: CPU-only and on a 2021-era 4 GB GTX 1650 Ti. Same GGUF, same binary, same prompts, one flag apart. The card takes decode by 4.3x, and needs only 1598 MiB to do it.
Dev.to | Sep 16, 2026 | xbill
Automated excerpt
Within-cell spread over three repeats was 6. 29% worst case on the CPU arm and 0. 84% on the GPU arm. CPU decode moves from 17. 61 to 15. 66 tok/s. The CPU arm ran first and saturated 12 cores.
Selected automatically from source text; not independently written or fact-checked. Read the original for full context.