brindusa/Qwen3.5-9B-heretic-v2
brindusa/Qwen3.5-9B-heretic-v2 is a 9 billion parameter language model, fine-tuned and converted to GGUF format using Unsloth. This model is designed for efficient deployment and inference, leveraging Unsloth's optimizations for faster training and conversion. It is suitable for general text-based applications and potentially multimodal use cases, as indicated by available GGUF files.
Loading preview...
Model Overview
brindusa/Qwen3.5-9B-heretic-v2 is a 9 billion parameter model that has been fine-tuned and subsequently converted into the GGUF format. This conversion process utilized Unsloth, a framework known for accelerating the training and conversion of large language models.
Key Characteristics
- Efficient Conversion: The model was processed with Unsloth, which facilitates faster training and GGUF conversion, making it optimized for deployment.
- GGUF Format: Available in GGUF format, ensuring compatibility with various inference engines like
llama.cpp. - Multimodal Potential: The presence of a
BF16-mmproj.gguffile suggests potential for multimodal applications, indicating it might support vision or other non-textual inputs.
Usage
This model is designed for use with llama-cli for text-only applications and llama-mtmd-cli for multimodal scenarios, leveraging the Jinja templating for prompts. The GGUF files provided include Qwen3.5-9B-heretic-v2.Q5_K_M.gguf and Qwen3.5-9B-heretic-v2.BF16-mmproj.gguf.