nomeda-lab/fattah-Orch-XS

TEXT GENERATIONConcurrency Cost:1Model Size:0.8BQuant:BF16Ctx Length:32kPublished:May 2, 2026License:apache-2.0Architecture:Transformer0.0K Open Weights Cold

The nomeda-lab/fattah-Orch-XS is a 0.6 billion parameter model from the Fattah-Orch family, developed by Nomeda Lab. This lightweight orchestrator is designed to process software requests in Egyptian Arabic, Modern Standard Arabic, or English, and output a structured JSON task graph. It specializes in breaking down complex coding requests into precise, typed, and dependency-ordered subtasks for subsequent execution by larger coder models. Its primary use case is to streamline the AI coding pipeline by providing clear instructions and reducing token usage for downstream models.

Loading preview...

Fattah-Orch-XS: Arabic-First Coding Orchestrator

Fattah-Orch-XS is a 0.6 billion parameter model, part of the Fattah-Orch family developed by Nomeda Lab. It functions as a lightweight orchestrator, designed to sit at the top of an AI coding pipeline. The model takes software requests in Egyptian Arabic, Modern Standard Arabic, or English and translates them into a structured JSON task graph, which can then be executed by other coding agents like GPT-4o or Claude.

Key Capabilities

  • Multilingual Input: Processes requests in Egyptian Arabic, Modern Standard Arabic, and English.
  • Task Orchestration: Breaks down high-level software requests into precise, typed, and dependency-ordered subtasks.
  • Structured Output: Generates a clean JSON task graph with request_summary, subtasks (including id, title, description, type, and depends_on).
  • Supported Task Types: Can define tasks for python, typescript, sql, go, kotlin, swift, and bash.
  • Efficiency: Aims to reduce ambiguity and token usage for downstream coder models by providing clear, pre-structured instructions.

Good For

  • Pre-processing coding requests: Ideal for preparing complex software development tasks before sending them to larger, more expensive code generation models.
  • Arabic-speaking developers: Offers native support for Arabic dialects, making it particularly useful for projects originating from Arabic specifications.
  • Optimizing AI coding workflows: Improves the quality and efficiency of code generation by ensuring coder models receive well-defined, structured tasks.
  • Lightweight deployment: The XS model is designed to run efficiently on any CPU, making it accessible for local or resource-constrained environments.

Finetunes
1 models