# EMLab releases KnowLine open-weight decision models from 0.8B to 31B parameters

> Original title: EMLab's KnowLine offers seven open-weight decision models for RAG, agent harnesses, and enterprise workflows, spanning dense models from ...

- Source: ModelScope
- Published: 2026-11-05T11:55:32.000Z
- Bad Influence: https://badinfluence.news/items/nttyej7mbebmfhbobnrc8or59
- Original: https://x.com/ModelScope2022/status/2118311247867490749

## Summary

EMLab's KnowLine offers seven open-weight decision models for RAG, agent harnesses, and enterprise workflows, spanning dense models from 0.8B to 31B plus two MoE options. KnowLine-31B-Gen1 scores 71.86 on Jev Decision Index 0.4.1 Full across private tests, and KnowLine-35B-A3B-Gen1.5 activates about 3B parameters with 47.1 ms median latency on a single RTX PRO 6000. Weights are released under Apache 2.0 and serving code under MIT.

## Post

EMLab's KnowLine offers seven open-weight decision models for RAG, agent harnesses, and enterprise workflows, spanning dense models from 0.8B to 31B plus two MoE options. 🤖https://modelscope.ai/collections/EMLab/KnowLine-Decision

🏆 SOTA on private decision tests: KnowLine-31B-Gen1 achieves 71.86 on Jev Decision Index 0.4.1 Full. The score combines private same-skill and new-domain tests, excluding public-suite results.

⚡ Low latency with sparse activation: KnowLine-35B-A3B-Gen1.5 activates about 3B parameters and scores 65.77 Full, with 47.1 ms median latency on the leaderboard's single RTX PRO 6000 setup.

✅ Measured probability calibration: In the 31B model's public-suite evaluation, approximately 0.9–1.0% of decisions made with at least 95% confidence were wrong. Validate thresholds on your own data.

🎯 Decisions throughout the workflow: Filter retrieved documents, check supporting evidence, select tools, route tickets, and score outputs through a Jev-compatible API supporting up to 64 questions per request.

🛠️ Adapt to your business: Continue post-training with ms-swift. The development loop uses research agents to construct and decontaminate data, train, evaluate, and retain or roll back changes based on evidence.

📜 Weights: Apache 2.0. Serving code: MIT.

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHWW_GkOb0AEETzi.jpg&mode=thumb&exp=1794096000&sig=aac3e9ed67d8f80b)

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHWW_VIjbYAA-U3P.jpg&mode=thumb&exp=1794096000&sig=c367eca279a52995)

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHWW_YBKagAAlSkC.jpg&mode=thumb&exp=1794096000&sig=0b976637d011bcb4)

[Video](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Famplify_video_thumb%2F2118309839923519489%2Fimg%2Fr6hOt5DWkuWxsUKp.jpg&mode=thumb&exp=1794096000&sig=6cb1e1ed18a06e44)