Gemma 3 4b Vision

Model

• https://huggingface.co/google/gemma-3-4b-it

• https://huggingface.co/lmstudio-community/gemma-3-4b-it-GGUF

Custom - HTTP POST

URL:

• http://127.0.0.1:1234/v1/chat/completions

Content Type:

• application/json

Headers:

• {}

Body:

{
  "model": "nanonets-ocr-s",
  "messages": [
    {
      "role": "system", "content": "You are a helpful assistant."
    },
    {
      "role": "user",
      "content": [        
        {
          "type": "image_url",
          "image_url": {
            "url": "data:image/jpeg;base64,$IMAGE_BASE64"
          }
        },
        { 
          "type": "text", 
          "text": "Extract the text from the image above as if you were reading it naturally. Return only valid words and complete sentences."
        }
      ]
    }
  ],
  "stream": false
}

Response Type:

• JSON

Response Query:

• choices[0].message.content