epsilonstar02/Qwen3.5_9B_Finetuned

VISIONConcurrency Cost:1Model Size:9BQuant:FP8Ctx Length:32kTool Calling:SupportedPublished:May 23, 2026Architecture:Transformer Cold

epsilonstar02/Qwen3.5_9B_Finetuned is a 9 billion parameter Qwen3.5 model, fine-tuned and converted to GGUF format using Unsloth. This model is optimized for efficient deployment and inference on local hardware, leveraging Unsloth's accelerated training and conversion process. It is suitable for general language tasks where a compact yet capable Qwen3.5 variant is desired.

Loading preview...

Overview

epsilonstar02/Qwen3.5_9B_Finetuned is a 9 billion parameter language model based on the Qwen3.5 architecture. This model has been fine-tuned and subsequently converted into the GGUF format, a common quantization format for efficient local inference, utilizing the Unsloth framework. Unsloth is highlighted for enabling 2x faster training and conversion processes.

Key Capabilities

  • Efficient Local Inference: Provided in GGUF format, making it suitable for deployment on consumer-grade hardware using tools like llama-cli.
  • Qwen3.5 Architecture: Leverages the capabilities of the Qwen3.5 base model.
  • Accelerated Development: Benefits from Unsloth's optimizations for faster fine-tuning and conversion.

Available Files

  • Qwen3.5-9B.Q4_K_M.gguf: A quantized version for balanced performance and size.
  • Qwen3.5-9B.BF16-mmproj.gguf: Includes multimodal projection capabilities, suggesting potential for multimodal applications.

Good For

  • Developers seeking a fine-tuned Qwen3.5 model for local deployment.
  • Applications requiring efficient inference with GGUF-compatible runtimes.
  • Experimentation with Qwen3.5's capabilities on optimized hardware.