Open decision models and reproductions with decision models

Open Jev-style text-and-image decision models built by a self-improving AI research loop, with an effort setting that picks depth.

Paused C#/.NET 10 non-autoregressive decision engine running a Laya/mmBERT checkpoint locally, returning Choice, Score and Boolean answers.

StartLux's open typed decision models from 0.8B to 27B plus a 35B-A3B MoE, reading text, JSON or images up to 256K tokens.

Reproducible test of SubQ Snap and Jev on 3,840 questions about a fictional store's event log from 2K to 360K tokens of context.

Open System One model and MLX runtime returning calibrated choice, score and noul probabilities via a Jev-compatible API.

Gemma 4 12B with its LM head replaced by a small answer head, serving Jev-style noul, choice and score decisions with custom code.

Together AI's experimental Qwen3.5 fine-tunes (4B and 0.8B) that pick one lettered option from a state, question and option list.

Open 1.9B typed-decision model that returns an option index and calibrated probability in one forward pass, with a paper and API.

Open Jev-style decision models with vision (Qwen3.5 4B/9B LoRA) serving Choice, Score and Noul on /v1/systemone.

SemIf (formerly OpenJev): reads typed option probabilities directly from open models like Qwen3.5-4B, including image inputs, on a home GPU.

Open Apache-2.0 4B decision model (Wald-Q4B) served via a Jev-compatible API, thinking only when unsure, with JevBench 210/231.

Open Apache-2.0 browser-agent decision model (Qwen3.5-35B-A3B fine-tune) that doubled Jev 1.13's task success in the same agent.

Apache-2.0 Gemma 4 12B fine-tune for local typed decisions, chat and image input, served via /v1/systemone and chat completions.

Static GGUF quantizations by mradermacher of SargeDev's JEV-27B-Uncensored, a Jev 1.13-distilled decision model.

Static GGUF quantizations by mradermacher of SargeDev's JEV-27B-VL-Uncensored vision decision model.

MIT-licensed benchmark and leaderboard for Jev-class decision models: accuracy, calibration, latency and cost on sealed tiers.

Reproduction kit for the Decision Index leaderboard: runs 37 public benchmarks against any /v1/systemone engine.

CUDA-native engine that serves open Qwen3.5 checkpoints behind a Jev-compatible API, reading option logits without decoding.

122M multilingual local decision model answering Choice, Noul and Score in milliseconds on CPU behind a /v1/systemone server.

Core ML and Neural Engine port of Laya for Apple Silicon, about 5 ms per short decision on an M3 Max with energy benchmarks.

Apple Silicon workbench running Laya, Decider, Kev and Jev side by side with accuracy, calibration, latency and memory benchmarks.

Runs jev-browser entirely on a local Jev-style engine (Qwen2.5 1.5B decisions, 0.5B typing) on an RTX 2060 SUPER, with no cloud API.

OpenJev: 151M ModernBERT decision model with RLCD-style calibration, a JevBench audit and an in-browser WebGPU playground.

Research framework for biomedical decision models on Qwen3.5, studying domain pretraining, NLI training, calibration and abstention.

Large rubric-classification benchmark of Jev vs Claude Haiku 4.5, Sonnet 5, OpenJev and many open models, with full price tracking.

Probability-aware evaluation of decision models: calibration, coverage at a fixed error budget and latency, Jev vs GLiNER2.5.

Reproducible benchmark comparing Jev with hosted and open decision models on rule application, probabilities, latency and cost.

100-question benchmark placing Jev's reasoning at 77% against small Qwen3.5 models under different thinking budgets.

Local benchmark comparing Jev with Laya-MLX on classifying GitHub issues for beginner-friendliness, CV fit and difficulty.

Speed and accuracy benchmark of hosted Jev 1.13 versus local Laya 421M on 1,470 synthetic items across eight decision tasks.