新Gemma 4 12B别看参数小，实测代码能力接近26B版，而且只需要9GB显存，16GB笔记本就能跑。
Google Gemma 4 12B模型在RTX 4090上实测仅需9GB VRAM，生成8.9k tokens，速度80 tok/s，性能接近26B版本。其对比的Gemma 4 26B-A4B使用15GB VRAM，生成6.9k tokens，速度138 tok/s，所有场景胜出。但12B在近半VRAM下表现十分接近，成为16GB笔记本的理想选择。
New Google Gemma 4 12B claims near-26B performance…
New Google Gemma 4 12B claims near-26B performance - we tested both!
We ran both models locally on one RTX 4090 and gave each the same task: write a self-contained HTML5 canvas animation with real physics in one file without libraries. Three scenes - a Galton board, two blocks colliding off a wall, and a chaotic triple pendulum
Outputs: Gemma 4 26B-A4B: 15 GB VRAM usage, 6.9k tokens, 138 tok/s Gemma 4 12B: 9 GB VRAM usage, 8.9k tokens, 80 tok/s
Same Gemma 4 family, but the 26B-A4B won every scene and ran ~1.7x faster - on just 4B active params. The 12B stayed very close though, on almost half the VRAM - which makes it the ideal model for a 16 GB laptop