X · by 生ビール
A Jev-style model running locally, with room to get faster.
生ビール
@wmoto_ai
ローカルTypesafe Jev、できたんやないか？ もうちょい速度は改善余地ありそう
Sep 17, 2026 · 383 likesOpen on X
生ビール (@wmoto_ai) shows a Jev-style model running on their own machine, and notes that its speed can still improve. The post is in Japanese.
Open the source
Luis Catacora
@lucataco
Cloudflare's new decision model can see 👀 clef-flash running locally on my M5 Max weights are Apache 2.0. go wild!
XOpen source
Jon Kraayenbrink
@kraayenJon
Jev repos blowing up right now. I made a list of the repos people are using to build with jev. 👇
Nick Khami
@skeptrune
you can make any open source model behave like jev with just a bit of inference engineering. it's shockingly easy. to prove it, we built a new endpoint we're calling deepseek-v4.1-flash-jev. see the demo below. here's how it's done: sglang (an inference engine) offers a scoring endpoint in addition to the normal generation one. in scoring mode, given an input & set of possible answers, it forces the model to produce probabilities for each one. example: > input: what is most common letter in abcccde? > possible answers: a, b, c > output: (c, 0.9), (b, 0.0.5), (a, 0.05) getting the above behavior instead of streamed output is as simple as using sglang's /v1/score endpoint instead of /generate. there's just one other trick required. for deepseek, you have to add a closing think tag before the response. this forces a direct answer instead of a reasoning trace. if you want reasoning, you can do that too, but imo that makes things too slow to be worth it. dsv4.1 flash is not as good as jev, but if we had enough spare compute to experiment with this same approach for a larger model then i think the decision quality would be at least as good, if not better. also, somewhat unrelated, i think decision-making models kill all prospecting & sourcing work. i would have absolutely killed to have jev or similar when i was recruiting @mintlify. absolutely incredible.
XOpen source