DarkKitsune/Qwen3.5-9B-Qworus-V2
DarkKitsune/Qwen3.5-9B-Qworus-V2 is a 9 billion parameter language model, a 50/50 DARE-TIES merge of empero-ai/Qwen3.8-9B-Distill and ornith-ai/Ornith-1.5-9B. This hybrid model is designed for enhanced reasoning capabilities, excelling in tasks such as coding, tool use, planning, and general question answering. It supports a context length of 32768 tokens and offers GGUF quantizations optimized for accuracy across various resource levels.
Loading preview...
Model Overview
DarkKitsune/Qwen3.5-9B-Qworus-V2 is a 9 billion parameter model created by DarkKitsune, resulting from a 50/50 DARE-TIES merge of empero-ai/Qwen3.8-9B-Distill and ornith-ai/Ornith-1.5-9B. This fusion aims to produce a robust hybrid reasoning model.
Key Capabilities
- Enhanced Reasoning: Designed to handle complex reasoning tasks effectively.
- Coding & Tool Use: Optimized for code generation, understanding, and integration with external tools.
- Planning & Design: Capable of assisting with planning and design-oriented challenges.
- General Question Answering: Provides comprehensive answers to a wide range of queries.
- GGUF Quantizations: Offers Q4_K_L and Q6_K_L quantizations, with imatrix training on a diverse mixture of code, business, math, and wikitext data. These quantizations feature bumped-up token embed, output layers (Q8_0), and ssm_* tensors (BF16/Q8_0) for improved accuracy, especially with longer contexts.
Intended Use
This model is primarily intended for testing and experimentation purposes. While it demonstrates strong capabilities in its specialized areas, it is not recommended for deployment in serious production projects.