cuongdk253/qwen36-35b-trajectory-16bit

TEXT GENERATIONConcurrent Unit Cost:3Model Size:35.1BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Jul 10, 2026Architecture:Transformer Featherless Exclusive Cold

The cuongdk253/qwen36-35b-trajectory-16bit is a 35.1 billion parameter Qwen3.6-35B-A3B model, finetuned by cuongdk253. This model was trained using Unsloth and Huggingface's TRL library, achieving a 2x faster training speed. It is designed for general language tasks, leveraging its large parameter count and efficient training methodology.

Loading preview...

Overview

This model, cuongdk253/qwen36-35b-trajectory-16bit, is a finetuned version of the Qwen3.6-35B-A3B architecture, developed by cuongdk253. It features 35.1 billion parameters and was trained with a focus on efficiency.

Key Characteristics

  • Base Model: Finetuned from Qwen/Qwen3.6-35B-A3B.
  • Training Efficiency: Achieved 2x faster training speeds by utilizing Unsloth and Huggingface's TRL library.
  • License: Distributed under the Apache-2.0 license.

Use Cases

This model is suitable for a broad range of natural language processing tasks, benefiting from its substantial parameter count and optimized training. Its efficient development process suggests potential for applications where rapid iteration and deployment are valuable.

Finetunes
1 models