Jared Palmer: 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 s…

jaredpalmer/kev-4b-20260924

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

Specifications & capabilities

Input
text
Output
decisions
Context window · tokens
8192
Published model ID
kev-4b
Capabilities
decisions
Description source ↗

Published prices

1–1 / 1

jaredpalmer/kev-4b ↗

$0.04

Inference provider
openRouter
Platform
OpenRouter
Unit
input_tokens_per_million
Currency
USD
Billing conditions

Source specification observations

1–2 / 2

openRouter ↗

field
context_length
value
8192
normalized value
8192
scope
source-model
source id
openRouter
confidence
1

openRouter ↗

field
max_output_tokens
value
7372
normalized value
7372
scope
source-model
source id
openRouter
confidence
1

Original sources

1–3 / 3

Hugging Face · jaredpalmer/kev-4b ↗

OpenRouter · Model page ↗

OpenRouter · Catalog ↗

Source links

1–2 / 2

Explore more models

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace