> ## Documentation Index
> Fetch the complete documentation index at: https://docs.comfy.org/llms.txt
> Use this file to discover all available pages before exploring further.

# Qwen 3.0 ComfyUI workflow example

> Qwen 3.0 is Alibaba Cloud's powerful open-source LLM with strong reasoning capabilities, available in 4B size for text generation and structured reasoning tasks.

<Tip>
  <Tabs>
    <Tab title="Portable or self deployed users">
      Make sure your ComfyUI is updated.

      * [Download ComfyUI](https://www.comfy.org/download)
      * [Update Guide](/installation/update_comfyui)

      Workflows in this guide can be found in the [Workflow Templates](/interface/features/template).
      If you can't find them in the template, your ComfyUI may be outdated. (Desktop version's update will delay sometime)

      If nodes are missing when loading a workflow, possible reasons:

      1. You are not using the latest ComfyUI version (Nightly version)
      2. Some nodes failed to import at startup
    </Tab>

    <Tab title="Desktop or Cloud users">
      * The Desktop is base on ComfyUI stable release, it will auto-update when there is a new Desktop stable release available.
      * [Cloud](https://cloud.comfy.org) will update after ComfyUI stable release.

      So, if you find any core node missing in this document, it might be because the new core nodes have not yet been released in the latest stable version. Please wait for the next stable release.
    </Tab>
  </Tabs>
</Tip>

**Qwen 3.0** (also known as Qwen3) is a powerful open-source LLM from Alibaba Cloud built for text generation, reasoning, and structured analysis. It is natively supported in ComfyUI through the built-in `TextGenerate` node.

**Model highlights**:

* **Strong reasoning** — Qwen3-4B-Thinking supports step-by-step chain-of-thought reasoning
* **Text generation focused** — optimized for structured text output, analysis, and coding tasks
* **ComfyUI native** — works with the built-in `TextGenerate` node, no custom nodes needed
* **Lightweight** — shares the same text encoder format as Qwen3.5, available in 2B, 4B, and 9B variants to fit different hardware

## Use Cases

Qwen 3.0 is well-suited for tasks that require structured text generation and intelligent reasoning within a ComfyUI workflow:

* **Prompt optimization** — feed existing prompts to Qwen 3.0 and ask it to rewrite, expand, or refine them for better image generation results. For example, convert a short keyword prompt into detailed, structured descriptions with style, lighting, and composition details.
* **Workflow logic reasoning** — use the model to analyze workflow parameters, suggest processing steps, or generate structured instructions that feed into other nodes.
* **Text-based analysis** — extract information, classify content, or generate structured reports from text inputs.
* **Chain-of-thought reasoning** — enable thinking mode for complex multi-step tasks that benefit from intermediate reasoning before producing the final output.

## Available workflow

### Qwen 3.0: Text Generation

<Card title="Download Workflow" icon="download" href="https://github.com/Comfy-Org/workflow_templates/blob/main/templates/llm_qwen3_text_gen.json">
  Download JSON or search "Qwen 3.0 Text Generation" in Template Library
</Card>

<Card title="Run on Comfy Cloud" icon="cloud" href="https://cloud.comfy.org/?template=llm_qwen3_text_gen&utm_source=docs&utm_medium=referral&utm_campaign=qwen3">
  Open in Comfy Cloud
</Card>

![Qwen 3.0 Text Generation Workflow](https://raw.githubusercontent.com/Comfy-Org/workflow_templates/main/templates/llm_qwen3_text_gen-1.webp)

This workflow demonstrates the core **text generation** capabilities of Qwen 3.0. It accepts a text prompt and generates detailed, structured responses using the model's built-in reasoning capabilities.

**Inputs**:

* **Text prompt** — your question, instruction, or task description

**Key controls**:

* **Max length** — maximum number of tokens to generate (default 256)
* **Sampling mode** — toggle sampling on/off and adjust temperature, top-k, top-p, repetition penalty, and seed
* **Thinking mode** — enable step-by-step reasoning before the final answer
* **Use default template** — apply the built-in system prompt for the model

**Output**:

* **Generated text** — the model's response as a plain text string

<Card title="Learn about Subgraph" icon="book-open" href="/interface/features/subgraph">
  This workflow uses Subgraph nodes for modular processing. Check out the Subgraph documentation to learn how to customize and extend the workflow.
</Card>

## Model Download

Qwen 3.0 models are loaded as text encoders in ComfyUI. The model files are shared with Qwen3.5 — download the variant that best fits your hardware:

<Card title="Qwen3.5 2B (bf16)" icon="download" href="https://huggingface.co/Comfy-Org/Qwen3.5/resolve/main/text_encoders/qwen3.5_2b_bf16.safetensors">
  Lightweight, \~4.5 GB. Best for low VRAM setups and fast downloads.
</Card>

<Card title="Qwen3.5 4B (bf16)" icon="download" href="https://huggingface.co/Comfy-Org/Qwen3.5/resolve/main/text_encoders/qwen3.5_4b_bf16.safetensors">
  Balanced size and quality. Recommended for most consumer GPUs.
</Card>

<Card title="Qwen3.5 9B (bf16)" icon="download" href="https://huggingface.co/Comfy-Org/Qwen3.5/resolve/main/text_encoders/qwen3.5_9b_bf16.safetensors">
  Largest variant, \~19 GB. Higher quality output, requires more VRAM.
</Card>

Place the downloaded `.safetensors` file in:

```
📂 ComfyUI/
├── 📂 models/
│   └── 📂 text_encoders/
│       └── qwen3.5_4b_bf16.safetensors   # or 2b / 9b variant
```