# Runbook: bu-30b-a3b-preview-AWQ-4bit Model on DGX Spark (Solo) with vLLM + Browser-Use **URL:** \ **Category:** DGX Spark / GB10 Projects\ **Created:** [February 4, 2026, 8:15pm UTC](https://forums.developer.nvidia.com/t/runbook-bu-30b-a3b-preview-awq-4bit-model-on-dgx-spark-solo-with-vllm-browser-use/359704 "2026-02-04T20:15:33Z")\ **Posts on this page:** 2\ **Page:** 1
**Author:** ![carlos.albarran.mx](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/carlos.albarran.mx/32/465538_2.png) [@carlos.albarran.mx](https://forums.developer.nvidia.com/u/carlos.albarran.mx)\ **Post date:** [February 4, 2026, 8:15pm UTC](https://forums.developer.nvidia.com/t/runbook-bu-30b-a3b-preview-awq-4bit-model-on-dgx-spark-solo-with-vllm-browser-use/359704/1 "2026-02-04T20:15:33Z")
This post walks through a complete, working setup for deploying the **cyankiwi/bu-30b-a3b-preview-AWQ-4bit** model on a **DGX Spark (GB10)** system using **vLLM** and consuming it from a lightweight agent application running in Docker (ChatGPY style) I tested this on a Single Spark… `bu-30b-a3b-preview-AWQ-4bit` Model and Why It Matters The **`bu-30b-a3b-preview-AWQ-4bit`** model is a **quantized, browser-use–optimized variant** of a larger Qwen-based architecture. It’s specifically tailored to work with the **Browser-Use OSS library** to provide **strong web interaction and browsing capabilities** for agent-style applications. 🔹 **Browser-Use Purpose** — This model is _heavily trained_ to understand and reason about web content and DOM structures, making it ideal for tasks where an agent needs to interact with web pages, interpret page layouts, extract information, and perform task-oriented browsing. 🔹 **Underlying Design** — The full “BU-30B-A3B-Preview” base model comes from a mixture-of-experts (MoE) version of the Qwen-VL-30B-A3B architecture, with efficient instruction and vision-language reasoning capabilities suitable for complex browsing and web tasks. The deployment is split into two parts: 1. **Model serving** (vLLM on DGX Spark GPUs) 2. **Client application** (Browser-Use agent calling the model via OpenAI-compatible API) * * * ## 1. Environment Overview **Hardware** - NVIDIA DGX Spark / GB10 - NVIDIA GPUs with sufficient VRAM for AWQ 4-bit 30B model **Software Components** - Docker + NVIDIA Container Toolkit - vLLM (OpenAI-compatible server) - Hugging Face model cache - Python 3.11 client container - Browser-Use + Playwright * * * ## 2. Download the Model (Optional but Recommended) Pre-downloading avoids repeated downloads inside containers. ```auto curl -LsSf https://astral.sh/uv/install.sh | sh uv --version uvx hf download cyankiwi/bu-30b-a3b-preview-AWQ-4bit ``` This places the model in your local Hugging Face cache: ```auto ~/.cache/huggingface ``` * * * ## 3. Start the vLLM Model Server on DGX Spark The following command launches a vLLM server optimized for DGX Spark, exposing an OpenAI-compatible API. ```auto docker run -d --privileged --gpus all --rm --ipc=host --network host --name bu30b \ -v ~/.cache/huggingface:/root/.cache/huggingface \ scitrera/dgx-spark-vllm:0.13.0-t4 \ vllm serve cyankiwi/bu-30b-a3b-preview-AWQ-4bit \ --gpu-memory-utilization 0.70 \ --served-model-name bu30b \ --max-model-len 65536 \ --host 0.0.0.0 --port 8000 ``` ### Key Flags Explained - `--served-model-name bu30b` Used by clients when specifying the model. - `--gpu-memory-utilization 0.70` Leaves headroom for stability on GB10. - `--max-model-len 65536` Enables long-context workloads. - `--network host` Simplifies access from client containers. Once running, the API is available at: ```auto http://127.0.0.1:8000/v1 ``` * * * ## 4. Client Application (Browser-Use Agent) The client runs in a separate Docker container and connects to the vLLM server. ### Dockerfile ```auto FROM python:3.11-slim ENV PYTHONDONTWRITEBYTECODE=1 ENV PYTHONUNBUFFERED=1 RUN apt-get update && apt-get install -y \ curl \ wget \ gnupg \ ca-certificates \ libnss3 \ libatk-bridge2.0-0 \ libxkbcommon0 \ libxcomposite1 \ libxrandr2 \ libxdamage1 \ libgbm1 \ libasound2 \ libxshmfence1 \ libgtk-3-0 \ libdrm2 \ libx11-xcb1 \ libxcb1 \ libxext6 \ libxfixes3 \ libxi6 \ libglib2.0-0 \ && rm -rf /var/lib/apt/lists/* WORKDIR /app COPY requirements.txt . RUN pip install --no-cache-dir -r requirements.txt RUN playwright install chromium COPY . . CMD ["python", "main.py"] ``` * * * ### requirements.txt ```auto browser-use python-dotenv playwright ``` * * * ### main.py ```auto from dotenv import load_dotenv from browser_use import Agent, ChatOpenAI load_dotenv() llm = ChatOpenAI( base_url='http://127.0.0.1:8000/v1', model='bu30b', temperature=0.6, top_p=0.95, dont_force_structured_output=True, # improves latency ) agent = Agent( task='Which is the top one topic of NVIDIA DGX Spark /GB10 User Forum - forums.developer.nvidia.com)', llm=llm, ) agent.run_sync() ``` * * * ## 5. Build and Run the Client Container ```auto docker build -t bu30b-client . docker run --rm --network host bu30b-client ``` Because both containers use `--network host`, the client can directly reach the vLLM server on `127.0.0.1:8000`. ![Screenshot from 2026-02-04 20-17-31](https://global.discourse-cdn.com/nvidia/original/4X/7/b/7/7b7fd4e50a1e8a8f0efcad4d02d5881e8e1aeacd.png) ---
**Author:** ![aniculescu](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/aniculescu/32/382649_2.png) [@aniculescu](https://forums.developer.nvidia.com/u/aniculescu)\ **Post date:** [February 4, 2026, 9:13pm UTC](https://forums.developer.nvidia.com/t/runbook-bu-30b-a3b-preview-awq-4bit-model-on-dgx-spark-solo-with-vllm-browser-use/359704/2 "2026-02-04T21:13:47Z")
Thanks for the overview! I have moved this to GB10 projects