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

# Mistral Small 4

export const MistralSmall4Deployment = () => {
  const modelId = 'mistralai/Mistral-Small-4-119B-2603';
  const options = {
    hardware: {
      name: 'hardware',
      title: 'Hardware Platform',
      getDynamicItems: values => {
        const isNvfp4 = values.quantization === 'fp4';
        return [{
          id: 'h100',
          label: 'H100',
          default: !isNvfp4,
          disabled: isNvfp4
        }, {
          id: 'h200',
          label: 'H200',
          default: false,
          disabled: isNvfp4
        }, {
          id: 'b200',
          label: 'B200',
          default: isNvfp4,
          disabled: false
        }, {
          id: 'b300',
          label: 'B300',
          default: false,
          disabled: false
        }];
      }
    },
    quantization: {
      name: 'quantization',
      title: 'Quantization',
      items: [{
        id: 'fp8',
        label: 'FP8',
        default: true
      }, {
        id: 'fp4',
        label: 'NVFP4',
        subtitle: 'Blackwell only',
        default: false
      }]
    },
    reasoning: {
      name: 'reasoning',
      title: 'Reasoning Parser',
      items: [{
        id: 'disabled',
        label: 'Disabled',
        default: false
      }, {
        id: 'enabled',
        label: 'Enabled',
        default: true
      }],
      commandRule: value => value === 'enabled' ? '--reasoning-parser mistral' : null
    },
    toolcall: {
      name: 'toolcall',
      title: 'Tool Call Parser',
      items: [{
        id: 'disabled',
        label: 'Disabled',
        default: false
      }, {
        id: 'enabled',
        label: 'Enabled',
        default: true
      }],
      commandRule: value => value === 'enabled' ? '--tool-call-parser mistral' : null
    },
    speculative: {
      name: 'speculative',
      title: 'Speculative Decoding (EAGLE)',
      items: [{
        id: 'disabled',
        label: 'Disabled',
        default: true
      }, {
        id: 'enabled',
        label: 'Enabled',
        default: false
      }],
      commandRule: value => value === 'enabled' ? '--speculative-algorithm EAGLE \\\n  --speculative-draft-model-path mistralai/Mistral-Small-4-119B-2603-eagle \\\n  --speculative-num-steps 3 \\\n  --speculative-eagle-topk 1 \\\n  --speculative-num-draft-tokens 4' : null
    }
  };
  const modelConfigs = {
    h100: {
      fp8: {
        tp: 2
      }
    },
    h200: {
      fp8: {
        tp: 2
      }
    },
    b200: {
      fp8: {
        tp: 1
      },
      fp4: {
        tp: 1
      }
    },
    b300: {
      fp8: {
        tp: 1
      },
      fp4: {
        tp: 1
      }
    }
  };
  const generateCommand = values => {
    const {hardware, quantization} = values;
    const hwConfig = modelConfigs[hardware]?.[quantization];
    if (!hwConfig) return `# Error: Unknown hardware/quantization combination`;
    const {tp} = hwConfig;
    const modelName = quantization === 'fp4' ? 'mistralai/Mistral-Small-4-119B-2603-NVFP4' : modelId;
    let cmd = `sglang serve --model-path ${modelName}`;
    cmd += ` \\\n  --tp ${tp}`;
    Object.entries(options).forEach(([key, option]) => {
      if (key === 'quantization' || key === 'hardware') return;
      if (option.commandRule) {
        const rule = option.commandRule(values[key]);
        if (rule) cmd += ` \\\n  ${rule}`;
      }
    });
    return cmd;
  };
  const getInitialState = () => {
    const initialState = {};
    Object.entries(options).forEach(([key, option]) => {
      if (option.type === 'checkbox') {
        initialState[key] = (option.items || []).filter(item => item.default).map(item => item.id);
        return;
      }
      if (option.type === 'text') {
        initialState[key] = option.default || '';
        return;
      }
      let items = option.items || [];
      if (option.getDynamicItems) {
        const defaultValues = {};
        Object.entries(options).forEach(([innerKey, innerOption]) => {
          if (innerOption.type === 'checkbox') {
            defaultValues[innerKey] = (innerOption.items || []).filter(item => item.default).map(item => item.id);
          } else if (innerOption.type === 'text') {
            defaultValues[innerKey] = innerOption.default || '';
          } else if (innerOption.items && innerOption.items.length > 0) {
            const defaultItem = innerOption.items.find(item => item.default);
            defaultValues[innerKey] = defaultItem ? defaultItem.id : innerOption.items[0].id;
          }
        });
        items = option.getDynamicItems(defaultValues);
      }
      const defaultItem = items && items.find(item => item.default);
      initialState[key] = defaultItem ? defaultItem.id : items && items[0] ? items[0].id : '';
    });
    return initialState;
  };
  const [values, setValues] = useState(getInitialState);
  const [isDark, setIsDark] = useState(false);
  useEffect(() => {
    const checkDarkMode = () => {
      const html = document.documentElement;
      const isDarkMode = html.classList.contains('dark') || html.getAttribute('data-theme') === 'dark' || html.style.colorScheme === 'dark';
      setIsDark(isDarkMode);
    };
    checkDarkMode();
    const observer = new MutationObserver(checkDarkMode);
    observer.observe(document.documentElement, {
      attributes: true,
      attributeFilter: ['class', 'data-theme', 'style']
    });
    return () => observer.disconnect();
  }, []);
  const handleRadioChange = (optionName, value) => {
    setValues(prev => ({
      ...prev,
      [optionName]: value
    }));
  };
  const handleCheckboxChange = (optionName, itemId, isChecked) => {
    setValues(prev => {
      const currentValues = prev[optionName] || [];
      if (isChecked) {
        return {
          ...prev,
          [optionName]: [...currentValues, itemId]
        };
      }
      return {
        ...prev,
        [optionName]: currentValues.filter(id => id !== itemId)
      };
    });
  };
  const handleTextChange = (optionName, value) => {
    setValues(prev => ({
      ...prev,
      [optionName]: value
    }));
  };
  const command = generateCommand(values);
  const containerStyle = {
    maxWidth: '900px',
    margin: '0 auto',
    display: 'flex',
    flexDirection: 'column',
    gap: '4px'
  };
  const cardStyle = {
    padding: '8px 12px',
    border: `1px solid ${isDark ? '#374151' : '#e5e7eb'}`,
    borderLeft: `3px solid ${isDark ? '#E85D4D' : '#D45D44'}`,
    borderRadius: '4px',
    display: 'flex',
    alignItems: 'center',
    gap: '12px',
    background: isDark ? '#1f2937' : '#fff'
  };
  const titleStyle = {
    fontSize: '13px',
    fontWeight: '600',
    minWidth: '140px',
    flexShrink: 0,
    color: isDark ? '#e5e7eb' : 'inherit'
  };
  const itemsStyle = {
    display: 'flex',
    rowGap: '2px',
    columnGap: '6px',
    flexWrap: 'wrap',
    alignItems: 'center',
    flex: 1
  };
  const labelBaseStyle = {
    padding: '4px 10px',
    border: `1px solid ${isDark ? '#9ca3af' : '#d1d5db'}`,
    borderRadius: '3px',
    cursor: 'pointer',
    display: 'inline-flex',
    flexDirection: 'column',
    alignItems: 'center',
    justifyContent: 'center',
    fontWeight: '500',
    fontSize: '13px',
    transition: 'all 0.2s',
    userSelect: 'none',
    minWidth: '45px',
    textAlign: 'center',
    flex: 1,
    background: isDark ? '#374151' : '#fff',
    color: isDark ? '#e5e7eb' : 'inherit'
  };
  const checkedStyle = {
    background: '#D45D44',
    color: 'white',
    borderColor: '#D45D44'
  };
  const disabledStyle = {
    cursor: 'not-allowed',
    opacity: 0.5
  };
  const subtitleStyle = {
    display: 'block',
    fontSize: '9px',
    marginTop: '1px',
    lineHeight: '1.1',
    opacity: 0.7
  };
  const textInputStyle = {
    flex: 1,
    padding: '8px 10px',
    borderRadius: '4px',
    border: `1px solid ${isDark ? '#4b5563' : '#d1d5db'}`,
    background: isDark ? '#111827' : '#fff',
    color: isDark ? '#e5e7eb' : '#111827',
    fontSize: '13px'
  };
  const commandDisplayStyle = {
    flex: 1,
    padding: '12px 16px',
    background: isDark ? '#111827' : '#f5f5f5',
    borderRadius: '6px',
    fontFamily: "'Menlo', 'Monaco', 'Courier New', monospace",
    fontSize: '12px',
    lineHeight: '1.5',
    color: isDark ? '#e5e7eb' : '#374151',
    whiteSpace: 'pre-wrap',
    overflowX: 'auto',
    margin: 0,
    border: `1px solid ${isDark ? '#374151' : '#e5e7eb'}`
  };
  return <div style={containerStyle} className="not-prose">
      {Object.entries(options).map(([key, option]) => {
    if (option.condition && !option.condition(values)) {
      return null;
    }
    const items = option.getDynamicItems ? option.getDynamicItems(values) : option.items || [];
    return <div key={key} style={cardStyle}>
            <div style={titleStyle}>{option.title}</div>
            <div style={itemsStyle}>
              {option.type === 'text' ? <input type="text" value={values[option.name] || ''} placeholder={option.placeholder || ''} onChange={event => handleTextChange(option.name, event.target.value)} style={textInputStyle} /> : option.type === 'checkbox' ? (option.items || []).map(item => {
      const isChecked = (values[option.name] || []).includes(item.id);
      const isDisabled = item.required || typeof item.disabledWhen === 'function' && item.disabledWhen(values);
      return <label key={item.id} title={item.disabledReason || ''} style={{
        ...labelBaseStyle,
        ...isChecked ? checkedStyle : {},
        ...isDisabled ? disabledStyle : {}
      }}>
                      <input type="checkbox" checked={isChecked} disabled={isDisabled} onChange={event => handleCheckboxChange(option.name, item.id, event.target.checked)} style={{
        display: 'none'
      }} />
                      {item.label}
                      {item.subtitle && <small style={{
        ...subtitleStyle,
        color: isChecked ? 'rgba(255,255,255,0.85)' : 'inherit'
      }}>
                          {item.subtitle}
                        </small>}
                    </label>;
    }) : items.map(item => {
      const isChecked = values[option.name] === item.id;
      const isDisabled = Boolean(item.disabled);
      return <label key={item.id} title={item.disabledReason || ''} style={{
        ...labelBaseStyle,
        ...isChecked ? checkedStyle : {},
        ...isDisabled ? disabledStyle : {}
      }}>
                      <input type="radio" name={option.name} value={item.id} checked={isChecked} disabled={isDisabled} onChange={() => !isDisabled && handleRadioChange(option.name, item.id)} style={{
        display: 'none'
      }} />
                      {item.label}
                      {item.subtitle && <small style={{
        ...subtitleStyle,
        color: isChecked ? 'rgba(255,255,255,0.85)' : 'inherit'
      }}>
                          {item.subtitle}
                        </small>}
                    </label>;
    })}
            </div>
          </div>;
  })}
      <div style={cardStyle}>
        <div style={titleStyle}>Run this Command:</div>
        <pre style={commandDisplayStyle}>{command}</pre>
      </div>
    </div>;
};

## 1. Model Introduction

**Mistral Small 4** is a powerful hybrid model from Mistral AI that unifies the capabilities of three different model families — **Instruct**, **Reasoning** (formerly called Magistral), and **Agentic (formerly called Devstral)** — into a single, unified model.

With its multimodal capabilities, efficient MoE architecture, and flexible mode switching, Mistral Small 4 is a versatile general-purpose model for virtually any task. In a latency-optimized setup, it achieves a 40% reduction in end-to-end completion time; in a throughput-optimized setup, it delivers 3× more requests per second compared to Mistral Small 3.

**Key Features:**

* **Hybrid Reasoning**: Switch between instant reply mode and deep reasoning/thinking mode — reasoning effort is configurable per request
* **Vision**: Accepts both text and image inputs, providing insights based on visual content
* **Function Calling**: Native tool calling and JSON output support with best-in-class agentic capabilities
* **Multilingual**: Supports dozens of languages including English, French, Spanish, German, Chinese, Japanese, Korean, Arabic, and more
* **Context Window**: 256K context window
* **Efficient MoE**: 119B total parameters, 128 experts, 4 active per token (6.5B activated parameters)
* **Apache 2.0 License**: Open-source, usable and modifiable for commercial and non-commercial purposes
* Reasoning effort supported are only **"none" and "high"**

**Architecture:**

* Same general architecture as Mistral 3
* MoE: 128 experts, 4 active per token
* 119B total parameters, 6.5B activated per token
* Multimodal input: text + image

**Models:**

* **[mistralai/Mistral-Small-4-119B-2603](https://huggingface.co/mistralai/Mistral-Small-4-119B-2603)** (FP8)
* **[mistralai/Mistral-Small-4-119B-2603-NVFP4](https://huggingface.co/mistralai/Mistral-Small-4-119B-2603-NVFP4)**
* **[mistralai/Leanstral-2603](https://huggingface.co/mistralai/Leanstral-2603)** — same architecture, use the same launch commands as Mistral-Small-4-119B-2603
* **[mistralai/Mistral-Small-4-119B-2603-eagle](https://huggingface.co/mistralai/Mistral-Small-4-119B-2603-eagle)** — EAGLE speculative decoding weights for faster inference

***

## 2. SGLang Installation

SGLang offers multiple installation methods. You can choose the most suitable installation method based on your hardware platform and requirements.

Please refer to the [official SGLang installation guide](../../../docs/get-started/install) for installation instructions.

<Info>
  Mistral Small 4 support landed in [sgl-project/sglang#20708](https://github.com/sgl-project/sglang/pull/20708) and has been merged into `main`. A model-specific Docker image is no longer required. Use the standard SGLang installation methods from the [official installation guide](../../../docs/get-started/install).
</Info>

***

## 3. Model Deployment

### 3.1 Basic Configuration

**Interactive Command Generator**: Use the configuration selector below to generate a launch command for Mistral Small 4.

<MistralSmall4Deployment />

### 3.2 Configuration Tips

* **Tensor Parallelism**: Mistral Small 4 FP8 (\~119 GB) requires tp=2 on Hopper (H100/H200), tp=1 on Blackwell (B200/B300). NVFP4 (\~60 GB, Blackwell only) runs with tp=1.
* **Reasoning effort**: Reasoning depth is configurable per request via `reasoning_effort` (`"none"`, `"high"`). No restart required — toggle per call.
* **Context length vs memory**: The model has a 256K context window. If you are memory-constrained, lower `--context-length` (e.g. `32768`) and increase once things are stable.
* **Tool calling**: Enable `--tool-call-parser mistral` to activate native function calling support.
* **Reasoning parser**: Enable `--reasoning-parser mistral` to separate `reasoning_content` from the main response content.
* **Speculative decoding (EAGLE)**: Enable with `--speculative-algorithm EAGLE --speculative-draft-model-path mistralai/Mistral-Small-4-119B-2603-eagle` using the [EAGLE weights](https://huggingface.co/mistralai/Mistral-Small-4-119B-2603-eagle) for lower latency.

***

## 4. Model Invocation

### 4.1 Thinking Mode

Mistral Small 4 is a hybrid reasoning model. By default, it does not produce a default reasoning response. Use `--reasoning_effort high` to toggle reasoning on.

```python Example theme={null}
from openai import OpenAI

client = OpenAI(
    base_url="http://localhost:30000/v1",
    api_key="EMPTY",
)

response = client.chat.completions.create(
    model="mistralai/Mistral-Small-4-119B-2603",
    messages=[
        {"role": "user", "content": "Solve step by step: what is 17 × 23 + 144 / 12?"},
    ],
    extra_body={"reasoning_effort": "high"},
)

print("Reasoning:", response.choices[0].message.reasoning_content)
print("Answer:", response.choices[0].message.content)
```

**Output:**

```text Output theme={null}
Reasoning: First, I'll break down the problem into two parts: the multiplication and
the division. According to the order of operations (PEMDAS/BODMAS), multiplication and
division are performed from left to right before addition.

17 × 23 = 17 × (20 + 3) = (17 × 20) + (17 × 3) = 340 + 51 = 391
144 / 12 = 12

Finally, add the results: 391 + 12 = 403

Answer: The solution to the problem is as follows:

1. First, perform the multiplication: 17 × 23.
   - 17 × 20 = 340
   - 17 × 3 = 51
   - 340 + 51 = 391

2. Then, perform the division: 144 / 12 = 12.

3. Finally, add the results:
   - 391 + 12 = 403

**Answer:** \boxed{403}
```

### 4.2 Instruct Mode (Reasoning Off)

To skip the reasoning trace and get a fast direct response, set `reasoning_effort` to `"none"`:

```python Example theme={null}
from openai import OpenAI

client = OpenAI(
    base_url="http://localhost:30000/v1",
    api_key="EMPTY",
)

response = client.chat.completions.create(
    model="mistralai/Mistral-Small-4-119B-2603",
    messages=[
        {"role": "user", "content": "Write a Python function to reverse a string."},
    ],
    extra_body={"reasoning_effort": "none"},
)

print(response.choices[0].message.content)
```

**Output:**

````text Output theme={null}
# Python Function to Reverse a String

Here are several ways to write a Python function to reverse a string:

## Method 1: Using String Slicing (Most Pythonic)
```python
def reverse_string(s):
    """Reverse a string using slicing."""
    return s[::-1]
```

## Method 2: Using a Loop
```python Example
def reverse_string(s):
    """Reverse a string using a loop."""
    reversed_str = ""
    for char in s:
        reversed_str = char + reversed_str
    return reversed_str
```

## Method 3: Using reversed() function
```python Example
def reverse_string(s):
    """Reverse a string using reversed() function."""
    return ''.join(reversed(s))
```

The first method using string slicing (`s[::-1]`) is generally the most efficient and
recommended approach in Python.

Example usage:
```python Example
original = "Hello, World!"
reversed_str = reverse_string(original)
print(reversed_str)  # Output: "!dlroW ,olleH"
```
````

### 4.3 Streaming with Reasoning

```python Example theme={null}
from openai import OpenAI

client = OpenAI(
    base_url="http://localhost:30000/v1",
    api_key="EMPTY",
)

stream = client.chat.completions.create(
    model="mistralai/Mistral-Small-4-119B-2603",
    messages=[
        {"role": "user", "content": "Explain the difference between async and threading in Python."},
    ],
    extra_body={"reasoning_effort": "high"},
    stream=True,
)

print("=== Reasoning ===")
for chunk in stream:
    delta = chunk.choices[0].delta
    if hasattr(delta, "reasoning_content") and delta.reasoning_content:
        print(delta.reasoning_content, end="", flush=True)
    elif delta.content:
        print("\n=== Response ===")
        print(delta.content, end="", flush=True)
print()
```

**Output:**

```text Output theme={null}
=== Reasoning ===
Okay, the user is asking about the difference between async and threading in Python.
I need to break this down clearly, covering the key aspects of both, like their
purposes, performance characteristics, and use cases...
=== Response ===
In Python, **`async`/`asyncio`** and **`threading`** are two different concurrency
models, each suited for specific use cases. Here's a breakdown of their key differences:

### 1. Model of Concurrency
- **Threading**: Based on preemptive multitasking using OS threads.
- **Async** (`asyncio`): Based on cooperative multitasking. Tasks voluntarily yield...
```

### 4.4 Tool Calling

Mistral Small 4 supports native function calling. Enable with `--tool-call-parser mistral`:

```python Example theme={null}
from openai import OpenAI

client = OpenAI(
    base_url="http://localhost:30000/v1",
    api_key="EMPTY",
)

tools = [
    {
        "type": "function",
        "function": {
            "name": "get_weather",
            "description": "Get the current weather for a city",
            "parameters": {
                "type": "object",
                "properties": {
                    "location": {"type": "string", "description": "City name"},
                    "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]},
                },
                "required": ["location"],
            },
        },
    }
]

response = client.chat.completions.create(
    model="mistralai/Mistral-Small-4-119B-2603",
    messages=[{"role": "user", "content": "What's the weather in Paris?"}],
    tools=tools,
    tool_choice="auto",
)

tool_calls = response.choices[0].message.tool_calls
for tc in tool_calls:
    print(f"Tool: {tc.function.name}")
    print(f"Args: {tc.function.arguments}")
```

**Output:**

```text Output theme={null}
Tool: get_weather
Args: {"location": "Paris"}
```

### 4.5 Vision (Image Input)

Mistral Small 4 accepts image inputs alongside text:

```python Example theme={null}
from openai import OpenAI

client = OpenAI(
    base_url="http://localhost:30000/v1",
    api_key="EMPTY",
)

response = client.chat.completions.create(
    model="mistralai/Mistral-Small-4-119B-2603",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "Describe what you see in this image."},
                {
                    "type": "image_url",
                    "image_url": {"url": "https://raw.githubusercontent.com/sgl-project/sglang/main/assets/logo.png"},
                },
            ],
        }
    ],
)

print(response.choices[0].message.content)
```

**Output:**

```text Output theme={null}
The image is a copyright symbol, represented by a stylized version of the lowercase
letter "c" inside a circle. The "c" is depicted in a white or light-colored font, and
the circle is orange. The design is simple yet striking, using oval and elliptical
shapes to create a distinct symbol which signifies copyright protection.
```

***

## 5. Benchmarks

### 5.1 Accuracy Benchmarks

#### GSM8K

```bash Command theme={null}
python3 benchmark/gsm8k/bench_sglang.py --port 30000
```

**Results:**

```text Output theme={null}
TODO
```

#### MMLU

```bash Command theme={null}
python3 benchmark/mmlu/bench_sglang.py --port 30000
```

**Results:**

```text Output theme={null}
TODO
```

### 5.2 Speed Benchmarks

#### Latency (Low Concurrency)

```bash Command theme={null}
python3 -m sglang.bench_serving \
  --backend sglang \
  --num-prompts 10 \
  --max-concurrency 1 \
  --random-input-len 1024 \
  --random-output-len 512 \
  --port 30000
```

**Results:**

```text Output theme={null}
TODO
```

#### Throughput (High Concurrency)

```bash Command theme={null}
python3 -m sglang.bench_serving \
  --backend sglang \
  --num-prompts 1000 \
  --max-concurrency 100 \
  --random-input-len 1024 \
  --random-output-len 512 \
  --port 30000
```

**Results:**

```text Output theme={null}
TODO
```