prithivMLmods/Vortex-9B-CodeCore-Merge

VISIONPricing:Input $0.431 / Cached $0.0862 / Output $1.12Concurrent Unit Cost:1Model Size:9BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Sep 17, 2026License:apache-2.0Architecture:Transformer0.0K Open Weights Featherless Exclusive Cold

Vortex-9B-CodeCore-Merge by prithivMLmods is a 9-billion parameter language model built upon Qwen3.5-9B, merged with NeoHorse-1-9B, Qwopus3.5-9B-Coder, and Ornith-1.5-9B. This model is specifically designed for advanced coding tasks, excelling in long-horizon code generation, multi-step problem solving, and agentic reasoning. With a 32768 token context length, it is optimized for complex software engineering workflows requiring sustained reasoning, code understanding, modification, and debugging.

Loading preview...

Vortex-9B-CodeCore-Merge: An Advanced Code & Reasoning Model

Vortex-9B-CodeCore-Merge is a 9-billion parameter experimental model developed by prithivMLmods, specifically engineered for complex coding and agentic reasoning tasks. It is constructed by merging the Qwen3.5-9B base model with three specialized models: NeoHorse-1-9B, Qwopus3.5-9B-Coder, and Ornith-1.5-9B. This unique merge strategy combines their strengths to create a model proficient in multi-step problem solving, instruction following, and autonomous coding workflows.

Key Capabilities

  • Long-Horizon Coding: Designed to handle extensive coding projects and sustained reasoning across multiple steps.
  • Agentic Coding & Reasoning: Optimized for autonomous coding workflows, including code understanding, modification, and debugging.
  • Multi-Step Problem Solving: Excels at tasks requiring sequential logical deduction and planning.
  • Instruction Following: Enhanced ability to interpret and execute complex instructions for software development.

Use Cases

This model is particularly suited for developers and researchers working on:

  • Complex software engineering tasks.
  • Automated code generation and refactoring.
  • Debugging and code analysis.
  • Agent-based development environments requiring advanced reasoning capabilities.

It's important to note that while powerful, this is an experimental model and may produce artifacts. GGUF versions are available, though they do not preserve Multi-Token Prediction (MTP) heads, operating as standard autoregressive decoders.

Finetunes
2 models