JevK5
39.2#139 of 261 on the open-weights board · Capability #107
Model guide · Open-weight Jev alternative · Qwen3.5-4B + distilled LoRA · updated October 26, 2026
The fastest open 4B on the board, with the weights published.
JevK5 answers the same yes/no, choice and score questions as Jev from open Qwen3.5-4B weights with a distilled LoRA merged in. It reads every option’s probability from the next-token logits in one forward pass on your own GPU, accepts the TypeSafe-style /v1/systemone request and is published under Apache-2.0. Version 0.3 is the current release and the one JevBench v1.7.48 ranks.
JevK5 is a third-party project by allebee. Jev AI does not host it; this page is a guide to what it is and how to run it yourself.
Try it on this page
Edit the example or paste your own text, then run it. Sign in to run: new accounts get 20 welcome credits, and a failed run costs nothing.
Jev AI does not host JevK5, so this editor runs Jev 1.14 on the same kind of decision. Compare the answers with your own JevK5 setup.
Support ticket triage · Jev 1.14
1 Input
Hi, this is the third time I am writing. Our payouts have failed every day since Monday and my team cannot pay suppliers. I already re-entered the bank details twice. If this is not fixed today we will have to move to another provider.
2 Questions
One benchmark measured every system under one method. It ranks 261 open-weights systems on one board and 54 hosted APIs on another; Jev, a hosted API, is ranked on the second and shown on the first as an unranked reference. The full board is on the JevBench results page.
JevK5
39.2#139 of 261 on the open-weights board · Capability #107
Jev 1.13.0
71.4Open-weights reference row · #18 of 54 on the API board · Capability #15
IntelligenceHow often it picks the right answer, half from sealed decisions
CalibrationWhether 0.8 really means about 80%
SpeedMeasured response time
Open half 38.3 · sealed half 38.7; chance-corrected by request type: choice 59.7, yes/no 21.7, score 34.2. The composite also weighs a fourth axis, cost, which these bars leave out. Self-hosted latency is adjusted by the benchmark to approximate production load.
JevK5 reads answers the way SemIf does: a softmax over the next-token logits of the answer letters, with one fitted temperature, so every option gets a probability in a single pass and nothing is generated. It states that it is not affiliated with TypeSafe and does not reproduce Jev’s unpublished architecture.
The training is what separates it from a plain logit reader. Qwen3.6-27B, with thinking, wrote documents carrying hard typed questions across 17 business domains and 11 decision families, answered each question twice, and kept it only when both answers matched. JevK5 was trained on 3,272 of those questions plus 3,272 human-labelled items from public datasets such as MMLU-Pro, BoolQ and banking77. The author states that no JevBench item and no Jev output was used.
The author documents a correction made on 23 September: a small hand-written set used to choose the calibration setting echoed the wording of a few public benchmark items. It was rewritten, and the author reports that no accuracy figure changed.
The repository appeared on 22 September 2026 and version 0.2.0 followed. JevBench v1.7.48 ranks version 0.3 #139 of 261 open-weights systems at 39.2, with intelligence 38.5, calibration 89.8 and the highest speed score of any system charted on this site, 93.8. Version 0.2 is #146 at 33.6. Jev, the board’s unranked reference, scores 71.4.
Plumb-4B, a LoRA fine-tune of JevK5 v0.2 by another author, ranks #112 at 50.4, twenty-three places above JevK5 itself: the base takes further fine-tuning well. On Benchmark Heaven’s Capability ranking, which averages intelligence and calibration, JevK5 v0.3 is #91.
JevK5 installs from GitHub as a Python package and ships a server that accepts the TypeSafe-style request shape. In bf16 it needs about 9 GB of GPU memory.
git clone https://github.com/allebee/jevk5
cd jevk5
# Follow README.md to install the package and start the server.
# The weights download from huggingface.co/alibiserikbay/JevK5 on first run.
curl http://localhost:8000/v1/systemone \
-H "Content-Type: application/json" \
-d '{"state": "Ticket: I was charged twice for the same month.",
"questions": {"team": {"type": "choice", "instructions": "Which team should handle this?",
"criteria": {"billing": null, "technical": null, "account": null}}}}'From the project’s own documentation and JevBench v1.7.48.
JevK5 is close enough that the honest comparison is on your own cases. Run them on Jev here — it takes a minute with no setup — and keep the answers: if JevK5 agrees on the cases you care about, you have a strong reason to self-host, and if it does not, you know exactly where the gap is.
An open-weight Jev alternative by allebee: Qwen3.5-4B with a distilled LoRA merged into the weights, published on Hugging Face as alibiserikbay/JevK5 under Apache-2.0. It answers noul, choice and score questions in one forward pass and ships a server that accepts the TypeSafe-style request.
No. It is a third-party project and states that it is not affiliated with TypeSafe AI. It does not reproduce Jev’s architecture.
Version 0.3, the current release. JevBench v1.7.48 ranks it #139 at 39.2 against version 0.2 at #146, with better intelligence, 38.5 against 36.3, and better calibration.
About 9 GB of GPU memory in bf16. The author’s published figures are on an H100 and an L40S.
Its server accepts the TypeSafe-style /v1/systemone request shape, so requests written for Jev need little or no change. Check the 16-option and 16,384-token limits first; the project does not claim full SDK compatibility.
It uses SemIf’s option-logit readout on the same Qwen3.5-4B base, then adds a distilled LoRA and a fitted temperature. Plumb-4B is a further LoRA fine-tune of JevK5 v0.2 by another author and ranks #112, above JevK5’s #139; SemIf is #183.
Every figure on this page is quoted from a published source and was read on October 26, 2026.
JevK5 and every other product named on this page belongs to its respective owner and is not affiliated with Jev AI. Figures are quoted from the sources above as they read on October 26, 2026 and can change.