license: apache-2.0
base_model: Qwen/Qwen3.6-35B-A3B
tags:
- gguf
- llama.cpp
- uncensored
- lora
- text-generation
Qwen3.6-35B-A3B-Uncensored-LoRA-GGUF
This repository contains GGUF-formatted files for Qwen3.6-35B-A3B-Uncensored-LoRA, a version of Alibaba's Qwen3.6-35B-A3B model with refusal behaviors removed via LoRA and MoE-specific abliteration techniques[reference:2].
Model Details
- Base Model: Qwen/Qwen3.6-35B-A3B
- Format: GGUF (for use with llama.cpp and compatible tools like Ollama, LM Studio, etc.)
- Architecture: MoE (35B total / 3B active parameters)
- Context Length: 262K tokens
- Modifications: Uncensored / Abliterated LoRA
Usage
You can load this GGUF file using any llama.cpp-based inference engine. For example, with llama.cpp:
llama-cli -m Qwen3.6-35B-A3B.gguf --lora Qwen3.6-35B-A3B-Uncensored-LoRA.gguf