Models

huihui_ai/qwenlong-l1.5-abliterated

QwenLong-L1.5, a long-context reasoning model built upon Qwen3-30B-A3B-Thinking, augmented with memory mechanisms to process tasks far beyond its physical context window.

ukjin/Qwen3-30B-A3B-Thinking-2507-Deepseek-v3.1-Distill

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.

SimonPu/qwen3

This repo contains both the Q4_K_XL version of Qwen3-30B-A3B-Instruct-2507 and Qwen3-30B-A3B-Thinking-2507

danielsheep/Qwen3-30B-A3B-Thinking-2507-Unsloth

Unsloth Dynamic 2.0 Quants achieves superior accuracy & SOTA quantization performance. UD-Q4_K_XL provided.

hopephoto/qwen3-30b-a3b-thinking_q8

transformed from qwen3-30b-a3b-thinking-2507

zantag/Qwen3-30B-A3B-Thinking-2507-GGUF-Q2_K_XL

odytrice/qwen3.6

Qwen 3.6 Ollama profiles for RTX 5090 across 27B dense and 35B-A3B MoE variants, with vision, thinking mode, and native tool calling.