ej

Product Hunt Models
edge-ai lightweight-model local-inference decision-making open-source cpu-inference

Summary

ej 是一个仅 11.4MB 的本地模型，专为运行时定义选项的类型化决策设计，可在 CPU 上单次前向推理输出概率分布，涵盖选择、是非与有序评分任务，并附带训练、评估与基准测试工具链。

<p> An 11MB local model for typed decisions in one pass </p> <p> <a href="https://www.producthunt.com/products/ej-jev-but-for-edge-devices?utm_campaign=producthunt-atom-posts-feed&amp;utm_medium=rss-feed&amp;utm_source=producthunt-atom-posts-feed">Discussion</a> | <a href="https://www.producthunt.com/r/p/1275189?app_id=339">Link</a> </p>
Original Article
View Cached Full Text

Cached at: 10/10/26, 08:32 AM

# ej: An 11MB local model for typed decisions in one pass | Product Hunt Source: [https://www.producthunt.com/products/ej-jev-but-for-edge-devices](https://www.producthunt.com/products/ej-jev-but-for-edge-devices) I built ej for a narrower problem than general classification: given some state and a set of decision questions whose options can be defined at runtime, return a probability distribution for each question in one pass\. It handles choice, yes/no, and ordered scores, runs on CPU, needs no token generation, and ships as one 11\.4 MB model file\. The repo includes training, evaluation, adaptation, packed weights, and the benchmark harness\.

Similar Articles

Microsoft-Decision-1

Product Hunt

Microsoft 推出 Decision-1 决策打分模型，用于代理与工作流的路由、分类、验证和控制，单次推理即可输出各选项的校准概率。该模型基于 Qwen3.5-9B 后训练，据称中位延迟比 GPT-6 Sol 快约 35 倍，现已在 Microsoft Foundry 上线。

@yibie: https://x.com/yibie/status/2104076142500069608

X AI KOLs Timeline

This article demonstrates how to convert GLM-5.3-Flash into a Jev-style System 1 decision model, achieving typed decisions through a single forward pass. Benchmark tests show that it performs comparably to specialized models in terms of accuracy and speed.

vllm-sr/d3

Hugging Face Models Trending

vllm-sr/d3 是 Decision 3.0 的 27B 多模态基础决策模型，支持文本、JSON、图像与视频输入，可在一次调用中完成选择、是非与评分决策并输出概率，无需生成文本。它在 Jev Decision Index 上以 66.3 排名官方文本榜第一，较 Decision 2.0 提升 10.4，并在 AMD MI325X 上实现 27 req/s 的服务性能。