从发布线程进入 Jev 技术博客
Diogo 在发布线程末尾给出官方技术博客与早期访问入口,适合继续核对模型原理和产品说明。
介绍Laya 421M作为显式Jev风格模型,体积0.85GB,jevbench准确率约50%,并推荐Mac本地使用GPT-OSS 20B和Gemma 4 E2B IT,iPhone上使用Laya或SmolVLM。
Laya 421M is the explicit jev-style model, at 0.85GB and ~50% jevbench accuracy. Check out the models in the readme, if you're doing things locally on your mac, GPT-OSS 20B and Gemma 4 E2B IT are pretty good. If you're doing things on an iPhone, prob go for Laya or SmolVLM