# Qwen3 30B A3B Instruct 2507 FP8

**Qwen3 30B A3B Instruct 2507 FP8** is an instruction-tuned large language model with 30 billion parameters, in FP8 precision. It reads text and returns text, for chat and question answering, summarization, multilingual tasks, mathematics and science problems, coding, and workflows that call tools. [AI Inference](/en/documentation/platform/ai-inference/) runs it under the id `Qwen/Qwen3-30B-A3B-Instruct-2507-FP8`.

## Model details

The id is the string a request passes to select this model, and `Azion.AI.run` takes it as the first argument. The HuggingFace repository publishes the model card.

| Detail                     | Value                                                                                               |
| -------------------------- | --------------------------------------------------------------------------------------------------- |
| Model name                 | Qwen3 30B A3B Instruct 2507 FP8                                                                     |
| Version                    | 30B - FP8                                                                                           |
| Model category             | Large Language Model (LLM)                                                                          |
| Model id                   | `Qwen/Qwen3-30B-A3B-Instruct-2507-FP8`                                                              |
| Size                       | 30B parameters                                                                                      |
| HuggingFace model          | [Qwen/Qwen3-30B-A3B-Instruct-2507-FP8](https://huggingface.co/Qwen/Qwen3-30B-A3B-Instruct-2507-FP8) |
| OpenAI-compatible endpoint | [OpenAI Chat API](https://developers.openai.com/api/reference/overview)                             |
| License                    | [Apache 2.0](https://choosealicense.com/licenses/apache-2.0/)                                       |

## Capabilities

The values below are properties of the model, and a request body does not set them. For the fields a request body does carry, with their types, defaults, and bounds, refer to [Model invocation](/en/documentation/platform/ai-inference/model-invocation/).

| Capability     | Value      |
| -------------- | ---------- |
| Input data     | Text       |
| Context length | 64k tokens |
| Tool calling   | Yes        |
| Supports LoRA  | Yes        |

The model's native context window upstream is larger, and 64k tokens is the context length AI Inference serves.

---

## Usage

The examples below call the model from a [function](/en/documentation/platform/functions/) with `Azion.AI.run`. The binding takes the model id as its first argument and the request body as its second, so the body never repeats the id. To send the same body to the OpenAI-compatible HTTP endpoint instead, refer to [Model invocation](/en/documentation/platform/ai-inference/model-invocation/).

### Chat completion

This request carries a system message that sets the role the model answers in, and a user message holding the prompt:

```ts
const modelResponse = await Azion.AI.run("Qwen/Qwen3-30B-A3B-Instruct-2507-FP8", {
  "stream": false,
  "messages": [
    { "role": "system", "content": "You are a helpful assistant." },
    { "role": "user", "content": "Name the European capitals." }
  ]
})
```

The call resolves to one response object, and the generated text sits at `modelResponse?.choices?.[0]?.message?.content`, the content of the first entry in `choices`.

### Tool calling

The same call becomes a tool-calling request when the body carries a `tools` array. Each entry sets `type` to `function` and holds a `function` object naming one function the model may call, what it does, and the `parameters` it takes in JSON Schema form:

```ts
const modelResponse = await Azion.AI.run("Qwen/Qwen3-30B-A3B-Instruct-2507-FP8", {
  "stream": false,
  "messages": [
    { "role": "system", "content": "You are a helpful assistant with access to tools." },
    { "role": "user", "content": "What is the weather in London?" }
  ],
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "get_weather",
        "description": "Get the current weather for a location",
        "parameters": {
          "type": "object",
          "properties": {
            "location": {
              "type": "string",
              "description": "The city and state"
            }
          },
          "required": ["location"]
        }
      }
    }
  ]
})
```

When the model selects a tool, the assistant message carries a `tool_calls` array instead of text, and each entry names the function and the arguments the model generated for it.

---

## Related resources

- [Model invocation](/en/documentation/platform/ai-inference/model-invocation.md): The fields a request body carries, and the HTTP form of the same call.
- [AI models](/en/documentation/platform/ai-inference/models.md): The rest of the catalog, with the id and the capabilities each model states.
- [AI Inference](/en/documentation/platform/ai-inference.md): The product this model runs on.
- [Functions](/en/documentation/platform/functions.md): The runtime that holds the binding the examples on this page call.
- [LoRA Fine-Tune](/en/documentation/platform/ai-inference/lora-fine-tune.md): The extension of AI Inference that adapts a model with LoRA, and the models that accept it.
- [Glossary](/en/documentation/platform/ai-inference/glossary.md): Definitions for model id, context length, and the other terms this page uses.