pritamdeka/Qwen3.6-35B-A3B-carexai-sft

TEXT GENERATIONConcurrency Cost:3Model Size:35.1BQuant:FP8Ctx Length:32kTool Calling:SupportedPublished:Jun 8, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

The pritamdeka/Qwen3.6-35B-A3B-carexai-sft is a 35.1 billion parameter Qwen3.6-A3B model, fine-tuned by pritamdeka using Unsloth and Huggingface's TRL library. This model is optimized for efficient training and deployment, leveraging Unsloth's speed enhancements. It is designed for general language understanding and generation tasks, building upon the capabilities of the Qwen3.6-A3B architecture.

Loading preview...

Model Overview

The pritamdeka/Qwen3.6-35B-A3B-carexai-sft is a 35.1 billion parameter language model, fine-tuned by pritamdeka. It is based on the Qwen3.6-A3B architecture and was developed with a focus on efficient training.

Key Characteristics

  • Base Model: Fine-tuned from unsloth/Qwen3.6-35B-A3B.
  • Training Efficiency: The fine-tuning process leveraged Unsloth and Huggingface's TRL library, enabling a 2x faster training speed compared to standard methods.
  • Parameter Count: Features 35.1 billion parameters, providing substantial capacity for complex language tasks.
  • Context Length: Supports a context length of 32768 tokens, allowing for processing and generating longer sequences of text.

Potential Use Cases

This model is suitable for applications requiring a large language model with efficient fine-tuning capabilities. Its foundation on the Qwen3.6-A3B architecture suggests applicability in areas such as:

  • General text generation and completion.
  • Question answering and summarization.
  • Conversational AI and chatbots.
  • Tasks benefiting from a large context window.