# Kev: Small Decision Models for Self-Training

> Train and run Jev-like decision models on your own with Kev.
- Title: Kev: Small Decision Models for Self-Training · GitHub
- Summary: Train and run Jev-like decision models on your own with Kev. Kev is a family of small decision models built on Qwen3.5/3.8 that you can train and run locally…
- Keywords: kev, qwen3.5, qwen3.8, decision models, self-training, customer support, type safe, modal, fine-tune, local deployment, technology, startups
- Source: GitHub — https://github.com/jaredpalmer/kev/tree/main
- Read time: 1 min
- Topics: kev, qwen3.5, qwen3.8, decision models, self-training, customer support, type safe, modal, fine-tune, local deployment, technology, startups
## What is Kev?
Kev is a family of small decision models built on Qwen3.5 and Qwen3.8.
## Key Features
Yes/no, multiple-choice, and rating questions in one request with calibrated probabilities.
## Drop-in for Jev
The TypeSafe Python SDK works against Kev servers unchanged.
## Model Sizes
Four sizes from 0.8B for laptops to 27B for data-center GPUs.
## Accuracy
Kev-27B matches Jev on new sources with 0.848 vs 0.857 accuracy.
## Local Deployment
Run Kev-4B locally with one command using Python and uv.
## Fine-Tuning
Fine-tune on your own labeled examples with a coding agent.
## Deployment
Deploy your own HTTPS endpoint with zero cost when idle.
## Use Case
Route customer support tickets with department, urgency, and frustration scores.
## Model Performance
Kev-4B answers six questions in 18.1 ms on an H100 GPU.
## Training
Train on public datasets and fine-tune with one epoch on 5,219 examples.
## Modal Deployment
Use Modal to deploy Kev with GPU scaling and zero cost when idle.
## Accuracy Comparison
Kev-27B trails Jev on knowledge questions but matches on new sources.
## Limitations
Calibration and date arithmetic are weaker than Jev for customer support.
## Self-Training
Kev learns from your data without needing a large dataset.
## What's Next
Kev will improve with more fine-tuning on customer support data.
## Key takeaway

Kev is a family of small decision models built on Qwen3.5/3.8 that you can train and run locally for customer support routing.