Kev: Tiny Jev-like family of decision models built on top of Qwen3.5

dunlin

Been hoping for something in this space. Jev-like decision models on Qwen3.5 could really simplify some of our internal routing logic.

mugul

Quite impressed by the energy people are putting into making OSS Jev-like models. I understand the hype but I wonder: what are the use cases for this kind of model? Could it be used in the context of coding agents, or is it more relevant in totally different situations?

monkeydust

Bit of a Jev explosion going on. Is it because it's taking us back to a simpler time we understand better? Classification models have been around for a while.

webprofusion

- https://github.com/logan-markewich/jeff - https://github.com/bespokelabsai/nimble

nullbio

I think a great use case for these will be when they have large context windows and are able to enforce styling rules for frontend development, and component creation rules for react. You can then ditch the styles guides and styling skills and create a decision tree for enforcing styling, so that you can't run into drift issues or duplication issues. That's where I'm wasting most of my time right now, constantly correcting all of the UX/UI issues that are created for every single feature.

raahelb

Because these decision models do not have tool calling, the knowledge cutoff might become a problem. We'll either have to keep training continuously if we run locally or switch to the newer version every month or so when using a closed one like Jev

jwr

I wonder how these would do filtering my spam. I have been using 27B-class models for a while now, and they are nearly perfect at determining what is spam and what isn't. The only disadvantage is computational cost.

faangguyindia

On Gemma 4 12B, I am getting 220 ms per move or QS. I used it to play the Snake game locally: prompt_eval=244 ms wall=245 ms schema_cache=hit generated=0 Move limit reached after 200 moves: score=16, length=19. So, if a 12B dense model can offer this latency on a local old PC, then definitely you can scale it up with more powerful machines and get even lower latency.

akkad33

Can someone tell me what is the difference between Jev and a normal neural network that does classification ? My understanding is: it takes text input and it does one shot classification (no training data)

Eastmill

Interesting approach with Qwen3.5 for decision models. Curious how "tiny" they've made them while keeping LLM reliability for critical paths.

rkeswick

Interesting to see a Jev-like approach applied to Qwen3.5. Always appreciated Jev's simplicity for quick decisions.

raahelb

The bright side of Jev being so popular could be that many companies and individuals realize that their applications might work well with a System One model, and they decide to run an open-source (or fine-tuned) version on their own

monxer

Why not name it Qev?

ingen0s

Oh Jared is cool - he made After and Razzle - nice

hbarka

If Jev is fundamentally trained using RLCD while you’re building on a Qwen model that was trained using RLHF, how can the resulting model be considered Jev-like?

andy12_

All the people that are just writing an Jev-like API on top of a normal LLM are missing the point. What makes Jev special is the training data; it's how it's trained. The architecture is probably nothing special. Just a text encoder with parallel prediction branches. I have tried many of these open-source Jev-like models on some linguistic tasks and they are so bad compared to Jev.

sinan-faizal

what kinda of specs would it need to run?

stackzero

looks high lev

scotty79

Distilling Jev should be super easy and cheap.

aetherspawn

I hope these get small and good enough to create “pet like” AIs for games. You know, like scream “follow me” at an NPC, STT stack translates it and feeds it to a local Jev-like model that then picks a number of things for the NPC to do.