Yeco Flash Mini-IT: The Italian Micro-LLM That Challenges Silicon Valley at Zero Cost
118M parameters, trained for under €15, ~200 tok/s on a consumer CPU. Yeco Flash Mini-IT is our proof of concept that sovereignty beats scale.
Marco Nasi
Ender-1 Enters Beta: Our Proprietary 3B Model Trained on EnderDevelopment Data
Ender-1 is our proprietary 3B model trained on EnderDevelopment data (free users, policy-compliant). It is in beta and rolling out on EnderDevelopment today.
Marco Nasi
Founder & CEO
Today Ender-1 enters beta. It is the first model of the Yeco LLM Series trained on our own platform data: EnderDevelopment, the gaming platform we already scaled to 20K active users.
What Ender-1 does
Ender-1 is a 3B-parameter proprietary model purpose-built for the gaming ecosystem. It generates Minecraft (Spigot/Paper) plugins, FiveM scripts, and Discord bots from natural-language intent — and repairs server configurations (YAML/JSON, BungeeCord/Velocity) when they break.
Trained on our data, within policy
The training corpus comes from EnderDevelopment free-tier activity, strictly within platform policy: feature requests, accepted outputs, compile results, and community-vetted configurations. No private or paid-tier data is used, ever.
Rolling out now
Ender-1 is in beta and rolling out on EnderDevelopment today. Real-world acceptance signals from the rollout feed the next training cycle — the same compact-model, rigorous-evaluation methodology behind Yeco-PII.
The gaming platform we scaled is now the training ground for our own model. That is the Yeco LLM Series thesis: every product generates the data that makes the next model better.
Related content
Official Release: Yeco-PII v1.0 · The Most Powerful PII Model, Built by Us
278M-parameter neural model for PII detection and anonymization. Native Italian, 6 European languages, average F1 0.966.
Marco Nasi
YecoAI Complies with AI Act, But Challenges Its Technical Feasibility
YecoAI publishes its position on the EU AI Act: full compliance with transparency obligations, with technical concerns on high-risk evaluation requirements.
Marco Nasi