Smallest Jev-like model
Summary
TinyDecide is a 10M-parameter Jev-like model (~6MB) that outperforms larger models on the Decision Index leaderboard and runs in browsers, Node.js, Python, Rust, and even on ESP32 microcontrollers.
Similar Articles
Trained locally: ultra-fast 0.8B/2B System 1 decision models that match Jev on benchmarks and Doom, ~30 ms per decision (open weights)
The Jeff models are ultra-fast, open-weight decision models trained locally on hardware like RTX PRO 6000, achieving competitive benchmarks against larger models like Jev with sub-30ms inference speeds.
qev-0.8b · New SOTA tiny local decision model
qev-0.8b is a 0.8B-parameter local decision model that takes a single forward pass to return calibrated probabilities over any input, ranking #1 of 27 similar-sized models on Benchmark Heaven (77.1%) at 3.5 ms p50 latency while running in 1.3 GB on a laptop. It ships in CUDA, MLX and GGUF formats and generalizes to games (Tetris, Pac-Man, 2048, Breakout, Whac-A-Mole) never seen in training.
Amazon releases its own Jev clone as decision models flood the web
Amazon Web Services released Strands Decider 2B, an open-source decision model inspired by TypeSafe's Jev, built on Qen3.5-2B to provide fast, low-cost, calibrated choice-making for agentic workflows instead of full LLM generation.
@svpino: Jev is incredibly good! If you haven't heard, Jev is a new "System One" model optimized for decision-making. For exampl…
Jev is a new AI model optimized for fast and cheap decision-making in classification tasks, demonstrated with a hotel review classifier project using Apify and GPT-5-mini.
From Text Decisions to Pixels: An Study of Jev-Style Visual Choice Model
PixelJev is introduced as a native-image decision interface using small open multimodal models to map images, instructions, and candidate sets to structured choices. The study demonstrates adaptation improves accuracy on benchmarks like Pets and highlights challenges in calibration and generalization.