Putting Jeff-1 out into the world, this is an attempt at a Jev like model, built on qwen…
This is a AI post classified by Jev as Open & local models (a model release), kept by the AI Radar because it carries real work, not commentary.
Putting Jeff-1 out into the world, this is an attempt at a Jev like model, built on qwen 4b. - Jeff does the job, can be ran locally. But I will say it is over confident, so id say use this to make a better jeff than me. https://huggingface.co/GestaltLabs/Jeff-1 I also included a how to train your own Jeff, this has been a cheap project as I have been able to do it on google collab entirely. It is a good first attempt, I have since had some realizations that will lead to the next version, currently in development.
Posted by Daniel Lougen (3.2k followers) 2 h ago · 23 likes · 814 views · view the original post on X. Kept by the AI Radar as Open & local models. Tools mentioned: jeff-1.
More AI work like this
- Meet DeepSeek-V4.1-Flash: a blazing fast image-text-to-text model. It takes both images… — @HuggingModels
- Meet Edge0-35B-A3B-preview: a 35B parameter MoE model built for edge inference. It runs… — @HuggingModels
- Train a 9M parameter language model from scratch in five minutes. — @tom_doerr
- Meet DeepSeek-R1-Distill-Qwen-Base-7B, a 7B text generation model fine-tuned for… — @HuggingModels
- Meet AliceAI-Foundation-80B-A3B-Base: a massive 80B parameter Mixture-of-Experts model… — @HuggingModels
- DeepSeek-v4.1-flash is really good with svg — @ItsmeAjayKV
- Jev launched Monday as a closed API. By Thursday we already have an open weight… — @plotarmordev
- Happy to see Qwen3.8-27B EXL3 works great for so many users. You can run it locally with… — @MiaAI_lab
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 27k posts from 4.8k X accounts over the last 14 days, 1.2k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 16:51 UTC. Full method.