ConnorYU/Qwen3.5-9B-Fish-30-1e

VISIONPricing:Input $0.431 / Cached $0.0862 / Output $1.12Concurrent Unit Cost:1Model Size:9BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Oct 7, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

ConnorYU/Qwen3.5-9B-Fish-30-1e is a 9 billion parameter language model developed by ConnorYU, fine-tuned from unsloth/Qwen3.5-9B. 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 efficient fine-tuning techniques to optimize performance.

Loading preview...

Overview

ConnorYU/Qwen3.5-9B-Fish-30-1e is a 9 billion parameter language model developed by ConnorYU. This model is a fine-tuned version of unsloth/Qwen3.5-9B, leveraging advanced training methodologies to enhance its capabilities. The fine-tuning process utilized Unsloth and Huggingface's TRL library, which enabled a significant acceleration in training speed, specifically achieving a 2x faster training rate.

Key Capabilities

  • Efficient Training: Benefits from Unsloth's optimizations for 2x faster fine-tuning.
  • General Language Understanding: Inherits the foundational capabilities of the Qwen3.5-9B base model.
  • Scalable Deployment: Suitable for applications requiring a 9B parameter model with optimized training.

Good For

  • Developers seeking a Qwen3.5-based model with enhanced training efficiency.
  • Applications where rapid iteration and fine-tuning are crucial.
  • General-purpose natural language processing tasks.

Finetunes
1 models