TeichAI/Qwen3-8B-Gemini-2.5-Flash-Distill

TEXT GENERATIONPricing:Input $0.468 / Output $1.82Concurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Nov 19, 2025License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

TeichAI/Qwen3-8B-Gemini-2.5-Flash-Distill is an 8 billion parameter language model developed by TeichAI, built upon the unsloth/Qwen3-8B base architecture. This model is specifically trained on a large Gemini 2.5 Flash dataset, making it particularly adept at tasks requiring broad knowledge. It is optimized for a wide range of applications including coding, science, legal, history, marketing, and general-purpose use cases.

Loading preview...

Model Overview

TeichAI/Qwen3-8B-Gemini-2.5-Flash-Distill is an 8 billion parameter language model developed by TeichAI. It leverages the unsloth/Qwen3-8B as its base architecture and has been extensively trained on the TeichAI/gemini-2.5-flash-11000x dataset. This specialized training on a large Gemini 2.5 Flash dataset is its primary differentiator, aiming to imbue the model with a broad and deep understanding across various domains.

Key Capabilities

  • Broad Domain Knowledge: Enhanced by training on a comprehensive Gemini 2.5 Flash dataset.
  • Versatile Application: Designed for a wide array of tasks.

Recommended Use Cases

This model is well-suited for applications requiring strong performance in diverse fields:

  • Coding: Assisting with code generation, understanding, and debugging.
  • Science: Processing and generating scientific information.
  • Legal: Handling legal texts and queries.
  • History: Engaging with historical data and narratives.
  • Marketing: Generating marketing content and insights.
  • General Purpose: Serving as a robust foundation for various everyday language tasks.

Finetunes
2 models