armand0e/Qwen3.6-35B-A3B-Fable-5-Distill

TEXT GENERATIONConcurrency Cost:3Model Size:35.1BQuant:FP8Ctx Length:32kTool Calling:SupportedPublished:Jun 30, 2026License:apache-2.0Architecture:Transformer0.0K Open Weights Cold

The armand0e/Qwen3.6-35B-A3B-Fable-5-Distill is a 35.1 billion parameter Qwen3.6-35B-A3B model, finetuned by armand0e. This model was trained using Unsloth and Huggingface's TRL library, achieving 2x faster training speeds. It is designed for general language tasks, leveraging its substantial parameter count and efficient training methodology.

Loading preview...

Model Overview

The armand0e/Qwen3.6-35B-A3B-Fable-5-Distill is a 35.1 billion parameter language model, finetuned by armand0e. It is based on the Qwen3.6-35B-A3B architecture and features a context length of 32768 tokens.

Key Characteristics

  • Efficient Training: This model was finetuned using Unsloth and Huggingface's TRL library, which enabled a 2x faster training process compared to standard methods.
  • Base Model: It is finetuned from the Qwen/Qwen3.6-35B-A3B model, inheriting its foundational capabilities.
  • Developer: Developed by armand0e.
  • License: Distributed under the Apache-2.0 license.

When to Consider This Model

  • General Language Tasks: Suitable for a broad range of natural language processing applications due to its large parameter count.
  • Efficiency Focus: Developers interested in models that leverage efficient training techniques like Unsloth for faster iteration and deployment.
  • Qwen Ecosystem: Users already familiar with or looking to integrate models from the Qwen family.

Finetunes
2 models