# Kev-27B

Decision models · checked 2026-10-25 · https://dbggr.dev/models/kev-27b/

Largest open-weight Kev decision model, fully fine-tuned Qwen3.8-27B; needs an 80 GB GPU

Kev-27B is an open-weight decision model from Jared Palmer (Apache 2.0, plus training code and eval suites, 27B, fully fine-tuned from Qwen3.8-27B (51 GB of weights) parameters): it answers typed questions, such as yes or no, pick one or pick several, with probabilities instead of writing text. There's no hosted version: you run it on your own hardware. It scores 78.9 (self-hosted; seconds are the board's estimate; not capability-ranked, as its cost is above the board's cap) on the independent JevBench Capability Score (board v1.7.46), where Jev, the reference, scores 77.1.

- Made by: Jared Palmer
- Weights: Open, Apache 2.0, plus training code and eval suites
- Size: 27B, fully fine-tuned from Qwen3.8-27B (51 GB of weights)
- Where: Self-host only
- Images: No, text only
- Context: 65,536
- Fine-tuning: Full recipe and a fine-tuning skill for coding agents published
- Docs: https://github.com/jaredpalmer/kev

## Kev-27B price

US dollars per million input tokens. Decision models don't write text, so none of the hosted ones charge for output.

| Where | Input | Output | Notes | Checked |
|---|---|---|---|---|
| Self-host only | Self-host | – | – | [2026-10-25](https://huggingface.co/jaredpalmer/kev-27b) |

## Kev-27B benchmarks

| Benchmark | Result | What it measures | Reported by |
|---|---|---|---|
| JevBench v1.7.46 | 78.9 | Capability Score: accuracy and calibration on typed decisions, with Jev as the reference system | [Independent](https://benchmarkheaven.com/jev-models) |
| JevBench time | 0.52 s | Seconds per decision: measured end to end for hosted APIs, the board's estimate for self-hosted models | [Independent](https://benchmarkheaven.com/jev-models) |
| Reported speed | 67.2 ms model time for six questions on an H200 | Latency on the maker's own hardware | Jared Palmer |

Makers' speeds are measured on their own hardware and aren't comparable with each other or with JevBench's timings.

## Decision models like Kev-27B

| Model | Input / M | JevBench | Weights |
|---|---|---|---|
| Kev-27B | Self-host | 78.9 | Open |
| [Mammoth-1](https://dbggr.dev/models/mammoth-1/) | Free | 85.2 | Open |
| [Perplexity Decider V1.2](https://dbggr.dev/models/pplx-decider-v1-2/) | $0.02 | 80.8 | Open |
| [d1-ultra](https://dbggr.dev/models/d1-ultra/) | $0.042 | 80.5 | Closed |
| [Clef](https://dbggr.dev/models/clef/) | $0.24 | 75.3 | Open |
| [Jev 1.14](https://dbggr.dev/models/jev/) | $0.042 | 75.0 | Closed |
| [d1](https://dbggr.dev/models/d1/) | $0.02 | 74.4 | Closed |
| [Mercury Decide](https://dbggr.dev/models/mercury-decide/) | $0.02 | 73.6 | Closed |
| [OpenAI Decisions (GPT-6 Luna)](https://dbggr.dev/models/openai-decisions/) | $0.10 | 73.5 | Closed |
| [Microsoft-Decision-1](https://dbggr.dev/models/microsoft-decision-1/) | $0.042 | 70.8 | Closed |
| [Elephant-1](https://dbggr.dev/models/elephant-1/) | Free | 70.2 | Open |
| [Strands Decider 26B-A4B](https://dbggr.dev/models/strands-decider-26b-a4b/) | Self-host | 66.7 | Open |
| [Clef-flash](https://dbggr.dev/models/clef-flash/) | $0.038 | 63.8 | Open |
| [Perplexity Decider Flash V1.2](https://dbggr.dev/models/pplx-decider-flash-v1-2/) | $0.01 | 61.7 | Open |
| [Clef-omni](https://dbggr.dev/models/clef-omni/) | $0.15 | 58.3 | Open |
| [d1-3B](https://dbggr.dev/models/d1-3b/) | Self-host | 49.5 | Open |
| [d1-omni-600M (experimental)](https://dbggr.dev/models/d1-omni-600m/) | Self-host | 32.8 | Open |
| [Laya](https://dbggr.dev/models/laya/) | Free | 32.5 | Open |
| [CLM-8B](https://dbggr.dev/models/clm-8b/) | Self-host | 20.1 | Open |
| [Clairic](https://dbggr.dev/models/clairic/) | $0.10 | – | Closed |
| [Kev-0.8B](https://dbggr.dev/models/kev-0-8b/) | Self-host | – | Open |
| [Kev-4B](https://dbggr.dev/models/kev-4b/) | Self-host | – | Open |
| [Kev-9B](https://dbggr.dev/models/kev-9b/) | Self-host | – | Open |
| [Strands Decider 2B](https://dbggr.dev/models/strands-decider-2b/) | Self-host | – | Open |

## FAQ

### How much does Kev-27B cost?

Kev-27B has no hosted, per-token price: you download it and run it yourself, so the cost is your own compute.

### Is Kev-27B open weight?

Yes. Jared Palmer publishes the weights under Apache 2.0, plus training code and eval suites, so you can run and fine-tune it yourself.

### How fast is Kev-27B?

Jared Palmer reports 67.2 ms model time for six questions on an H200, measured on its own hardware. JevBench gives 0.52 seconds per decision, its estimate for self-hosting.

### How does Kev-27B compare with Jev?

On JevBench's Capability Score (board v1.7.46), Kev-27B scores 78.9 against Jev's 77.1. Jev costs $0.042 per million input tokens; Kev-27B is self-host only. JevBench is a one-person project that uses Jev as its reference, which favours cheap hosted models.