https://huggingface.co/Contrastive-LM/CLM-v0.1-8B
https://huggingface.co/crh225/plumb-4b
https://huggingface.co/denis-pplx/autojev-27b
https://huggingface.co/Falconsai/LightDec
https://huggingface.co/Falconsai/LightDec_V2
https://huggingface.co/fastino/GLiNER2.5-Decide
https://huggingface.co/internlm/Intern-Decision-4B
https://huggingface.co/kitaniai/OpenJudgement-4B-Preview
https://huggingface.co/Kwokou/BeeNara
https://huggingface.co/manjunathshiva/opendecider-small-td-GGUF
https://huggingface.co/mohit67890/imajev-4b
https://huggingface.co/Mr-Shmoo/sonda-1.0-4B
https://huggingface.co/mstrasser/Jeff-Qwen3.5-0.8B-emotion
https://huggingface.co/mstrasser/Jeff-Qwen3.5-2B
https://huggingface.co/n4ze3m/Qwen3.5-4B-Hmm
https://huggingface.co/OmniJev/OneJev-0.8B
https://huggingface.co/org2ai/Wald-4B
https://huggingface.co/Reza2kn/Bev
https://huggingface.co/richardyoung/Bev-9B-inverted
https://huggingface.co/SargeDev/Jev_Qwen3.8-27B
https://huggingface.co/startlux-models/StartLux-Decision-4B
https://huggingface.co/startlux-models/StartLux-Decision-9B
https://huggingface.co/SupersonicLabs/Julia-1
https://huggingface.co/togethercomputer/Tev1-4B-experimental
This one supposedly beats Jev at its own game:
https://huggingface.co/Cloudflare/clef (27B)
https://huggingface.co/Cloudflare/clef-flash (9B)
Requires a modded llama-server to run, but I find this project especially interesting. They have extracted the fine-tuning and decision making head from Clef (which is a modded Qwen3.8-27B), to make it possible to run both Clef and normal Qwen at the same time, while sharing the majority of the parameters.
Interesting list. These caught my eye when I was looking into this a couple weeks ago, but I haven’t gotten around to trying them out yet:
