Qwen3 4B PARO

--- library_name: transformers license: apache-2.0 pipeline_tag: text-generation base_model: - Qwen/Qwen3-4B tags: - mlx --- # z-lab/Qwen3-4B-PARO **Pairwise Rotation Quantization for Efficient Reasoning LLM Inference** <p> <a href="https://arxiv.org/abs/2511.10645"><img src="https://img.shields.io/badge/arXiv-2511.10645-b31b1b.svg" alt="Paper"></a> <a href="https://paroquant.z-lab.ai"><img src="https://img.shields.io/badge/Blog-ParoQuant-blue" alt="Blog"></a> <a href="https://huggingface.co/collections/z-lab/paroquant"><img src="https://img.shields.io/badge/%F0%9F%A4%97-Models-yellow" alt="Models"></a> <a href="https://pypi.org/project/paroquant/"><img src="https://img.shields.io/pypi/v/paroquant" alt="PyPI"></a> </p> ParoQuant is the state-of-the-art INT4 quantization for LLMs. It closes the accuracy gap with FP16 while running at near-AWQ speed. Supports NVIDIA GPUs (vLLM, Transformers) and Apple Silicon (MLX). For more information, see https://github.com/z-lab/paroquant. z-lab/Qwen3-4B-PARO is a 4-bit [Qwen/Qwen3-4B](https://huggingface.co/Qwen/Qwen3-4B) quantized with ParoQuant. Check out other ParoQuant models from the Hugging Face [collection](https://huggingface.co/collections/z-lab/paroquant). ## Quick Start ### Installation ```bash # NVIDIA GPU (CUDA 12.9) pip install "paroquant[vllm]" # NVIDIA GPU (CUDA 13.0) pip install "paroquant[vllm]" "vllm==0.19.1" \ --extra-index-url https://wheels.vllm.ai/0.19.1/cu130 \ --extra-index-url https://download.pytorch.org/whl/cu130 # Apple Silicon pip install "paroquant[mlx]" ``` ### Interactive Chat ```bash python -m paroquant.cli.chat --model z-lab/Qwen3-4B-PARO ``` ### OpenAI-Compatible API Server For vLLM, you can directly use `vllm serve` to serve ParoQuant models: ```bash vllm serve z-lab/Qwen3-4B-PARO --port 8000 ``` For other frameworks: ```bash python -m paroquant.cli.serve --model z-lab/Qwen3-4B-PARO --port 8000 ``` ### Docker (NVIDIA GPU) > [!NOTE] > The following commands map the local cache directory to the container in order to persist kernel cache across runs. Remove `-v ...` to disable this behavior. ```bash # Interactive chat docker run --pull=always --rm -it --gpus all --ipc=host \ -v $HOME/.cache/paroquant:/root/.cache/paroquant \ ghcr.io/z-lab/paroquant:chat --model z-lab/Qwen3-4B-PARO # API server (port 8000) docker run --pull=always --rm -it --gpus all --ipc=...

Source context: 66 downloads · 2 likes · Pipeline text-generation · Library transformers · Repo z-lab/Qwen3-4B-PARO

Source context: 297 downloads · 2 likes · Pipeline text-generation · Library transformers · Repo z-lab/Qwen3-4B-PARO