README.md

metadata

title: Huihui Qwen3.8 27B Abliterated GGUF
emoji: ⚡
colorFrom: indigo
colorTo: purple
sdk: gradio
sdk_version: 6.25.0
python_version: '3.12'
app_file: app.py
pinned: false
short_description: Chat demo for Huihui Qwen3.8 27B Abliterated GGUF

Huihui Qwen3.8 27B Abliterated (GGUF) Demo

Conversational chat demo running huihui-ai/Huihui-Qwen3.8-27B-abliterated-GGUF using llama.cpp on Hugging Face ZeroGPU.

Features

• Fast Inference: Uses GGUF quantization with GPU offloading via llama-cpp-python.
• ZeroGPU Acceleration: Dynamic GPU allocation on NVIDIA GPUs.
• Streaming Responses: Real-time response streaming into a modern bubble chatbot UI.
• Configurable Generation: Customizable system prompt, temperature, top-p, top-k, repetition penalty, and max tokens.
• MCP Server Ready: Built-in Model Context Protocol server support (mcp_server=True).

Notice

This model has significantly reduced safety refusal filtering. It may generate sensitive or uncensored content. You are responsible for adhering to applicable laws and policies.