Local runtimes and serving with decision models

Open, local Jev-style server on llama.cpp that returns typed decisions from a fine-tuned Spark-X2.5-4B without generating tokens.

Local Jev-compatible /v1/systemone server that reads typed answers from the logits of any MLX or OpenAI-compatible model, no training.

Standard Thinking's Apache-2.0 3B and 8B decision models on Ministral 3 that score bounded answers via /v1/systemone, with vision.

Rust server on candle that serves open decision models like Laya and Clef behind a System One-compatible API with dynamic batching.

Runs Laya System 1 models on a Mac's GPU in Rust with custom Metal kernels, serving the same /v1/systemone API as laya serve.

Open 596M and 4B decision models that answer Choice, Score and Noul in one pass locally, with calibrated confidence for escalation.

Apache-2.0 118M multilingual decision model for Choice, Score and Noul on the System One API, with conformal abstain.

Apache-2.0 395M ModernBERT System One model serving calibrated Choice, Noul and Score locally as a drop-in /v1/systemone replacement.

Apache-2.0 ModernBERT decision model answering Noul, Choice, Score and multi-label questions, with a local Jev-compatible server.

OpenJevPro: typed Choice/Noul/Score API over open LLMs, Laya or Jev with order-invariant scoring and a System 2-to-1 distillation flywheel.

Deploys DiffusionGemma-Jev behind a TypeSafe-compatible API on a Cloud Run GPU, with snake, dino and tetris demos.

CPU port of SemIf that reads typed decisions from a small open model's option logits on a laptop, with a web UI.

Tiny /v1/systemone-compatible decision server: a 7M-parameter CPU model in an 8 MB native binary, with conformal abstention.

Unofficial proof of concept serving Jev's /v1/systemone shape from a local BERT-style zero-shot classifier, with honest caveats.

GitHub Next's Bun server that exposes a Jev-compatible /v1/systemone API by asking DiffusionGemma for probabilities via a chat endpoint.

Serves MiniCPM5-2B-8bit on Apple Silicon as a Jev-compatible /v1/systemone service and reproduces its JevBench score.

Gemma 3 4B option scorer that prefills context once and scores all options in one pass, on MLX or PyTorch, with a Doom demo.

Experimental iPhone app for on-device visual decisions: Qwen3-VL on MLX reads option-letter logits for 2-26 choices about a photo.

Chinese local MLX demo that scores 2-5 candidate decisions with a small Qwen model and drives a Snake game by choosing among moves.

Training-free runtime turning local Qwen3/Qwen3.5 checkpoints into a Jev-style Noul/Choice/Score service via candidate-token logits.

Formerly OpenJev: open-model 'semantic ifs' that read option logits from a frozen 4B model on one RTX 3090, with a browser demo.

Archived early Jev-compatible API server running Qwen3.6-35B-A3B prefill-only on SGLang via Modal; superseded by SGLang's native endpoint.

Small open decision model on a frozen Qwen3.5-4B serving /v1/systemone in about 200 ms, benchmarked against Jev on JevBench.

Open-weight 0.6B decision model on a Qwen3 backbone: state and typed questions in, a probability for every option out, nothing decoded.

Open 27B multimodal decision model built largely by autonomous agents, serving choice, noul and score on a TypeSafe-compatible API.

Experimental 17M-400M English decision models for choice, yes/no, score and reranking, with weights, training code and an ONNX browser demo.

Bespoke Labs' open recipe, data and 9B LoRA model for Jev-style choice and true/false decisions, runnable on Apple Silicon or NVIDIA GPUs.

Open Apache-2.0 Jev-like model family on Qwen3.8-27B that reads one-token candidate preferences and serves a TypeSafe-compatible API.

399M ModernBERT-large decision model with one universal choice head answering Choice, Noul and Score in a single forward pass.

Open Apache-2.0 System One decision models (4B, 9B, 27B on Qwen) with trainer, data builders, evals and every run record.