Tagged "model-specialization"
5 articles tagged model-specialization, 26 February 2026 to 9 October 2026. Newest first.
-
JetBrains Releases Mellum 2.1: 12B MoE Model Optimised for Coding Agents
JetBrains released Mellum 2.1, a 12 billion parameter Mixture-of-Experts model designed specifically for coding tasks and agentic workflows, available as an open-source model.
-
Agentic AI Community Focus: Building Local Agents in 2026
The emerging agentic AI community shares resources and frameworks for building autonomous agents with local LLM backends. Focus areas include memory systems, tool integration, and edge deployment of multi-step reasoning tasks.
-
FretBench – Testing 14 LLMs on Reading Guitar Tabs Reveals Performance Gaps
A comprehensive benchmark evaluating 14 different LLMs on their ability to parse and understand guitar tablature exposes significant performance variations across models.
-
Jan Releases Code-Tuned 4B Model for Efficient Local Code Generation and Development Tasks
The Jan team open-sources Jan-Code-4B, a specialized 4-billion parameter model fine-tuned for code generation, refactoring, debugging, and test writing while optimizing for local deployment and efficiency.
-
Agent System – 7 specialized AI agents that plan, build, verify, and ship code
A new multi-agent system coordinates seven specialized agents to handle planning, development, verification, and deployment of code. This demonstrates practical frameworks for orchestrating local LLMs in complex workflows.