7 models
pulled as BF16, vocab slice (combined_en_huge) requant to IQ4_NL (combined_en_huge) -- (English + Coding focus) - ~20% faster than Q4_K_M
full BF16 model, hand-requant to IQ4_NL, with combined_en_huge dataset (English + Coding focus)
High Quality Vision Instruct Model
Recommended for transcribing and summarizing text from screenshots.
This model is a distilled version of Qwen/Qwen3-30B-A3B-Instruct designed to inherit the reasoning and behavioral characteristics of its much larger teacher model, deepseek-ai/DeepSeek-V3.1.
Quantized version of Qwen3 models (4B,8B,14B,32B, 30B-moe) optimized for tool usage in Cline / Roo Code and solving Complex Problems.