The open-source local version Laya's response speed crushes

@NFT_Chen SuSu_酥酥👅 · Sep 20, 2026 · case #338229 · listed via Jev Hub

Still from the clip posted with this case; watch it in the original post on X.

Benchmarked local 421M model Laya against Jev 1.13.0 on the same snake game with identical typed decisions, measuring decisions per second and P50 latency.

The original post, translated

💥It blew up! The open-source local version Laya's response speed crushes Jev, millisecond-level decisions are lightning fast! On the left, Laya is a local 421M open-source decision model, on the right, Jev 1.13.0 is a cloud API. Same game of Snake, same set of typed decision, after 30 seconds of free running: 🔹Laya: score 46, length 52, decisions 86.5 per second, P50 about 9ms 🔸Jev: score 1, length 7, decisions 3.2

Show the original post in its source language ▾

💥炸了！开源本地版 Laya 响应速度吊打 Jev ，毫秒级决策快到飞起！左边 Laya 是本地 421M 开源决策模型，右边 Jev 1.13.0 是云端 API。同一盘贪吃蛇、同一套 typed decision，30 秒自由跑下来： 🔹Laya：分数 46、长度 52，决策 86.5 次/秒，P50 约 9ms 🔸Jev：分数 1、长度 7，决策 3.2

The post above is a machine translation from zh; the untranslated text is in the fold-out.

Engagement when collected

Views365K

Likes95

Bookmarks0

Reposts0

Replies0

Quotes0

Numbers are a snapshot taken from X when the case was added to the library (schema v1, collected 2026-09-19); they will not match today.

Where this case fits

Filed under coding & developer tools. In the pattern Jev is built for, the model answers a bounded question per step — and ordinary code acts on the answer, because the answer is already a value rather than a paragraph. Other posts in the same family are on the coding & developer tools page.

🛠️ Coding & developer tools