Models Model details

Jared Palmer

Jared Palmer: Kev 4B

jaredpalmer/kev-4b

Kev 4B is a small open-weight decision model from Jared Palmer, built as a LoRA adapter and pointer head on Qwen3.5-4B-Base and served over the same /v1/systemone contract as TypeSafe's Jev. Send a state and typed questions (yes/no, multiple choice, or score) and it returns a calibrated probability per question in one forward pass, with no generated text. It is the recommended checkpoint in the Kev family (0.8B, 4B, 9B) and is suited for routing, classification, and policy checks that want a compact, Apache-2.0 alternative to Jev. Code, model cards, and eval suites: https://github.com/jaredpalmer/kev

Input
$0.042

/ 1M tokens · Token reference

Output
$0

/ 1M tokens · Token reference

Context window
8.19K

tokens

Decisions output · Token reference fields do not establish an output-unit price.

Limits

Context

8,192

tokens

Max output

7,372

90% of the context window

Model facts

Author

Jared Palmer

Tokenizer

Other

Modality

Text -> Decisions

License

Apache-2.0

Created

Sep 25, 2026

Hugging Face

jaredpalmer/kev-4b

Publication status

Hugging Face: verifiedLicense: publishedParameter count: not published

Modalities

Input · TextOutput · Decisions