ibm/granite3.2-vision

ibm/ granite3.2-vision

128 Downloads Updated 7 months ago

vision tools 2b

ollama run ibm/granite3.2-vision:2b

curl http://localhost:11434/api/chat \
  -d '{
    "model": "ibm/granite3.2-vision:2b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='ibm/granite3.2-vision:2b',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'ibm/granite3.2-vision:2b',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Applications

Claude Code ollama launch claude --model ibm/granite3.2-vision:2b

Codex ollama launch codex --model ibm/granite3.2-vision:2b

OpenCode ollama launch opencode --model ibm/granite3.2-vision:2b

OpenClaw ollama launch openclaw --model ibm/granite3.2-vision:2b

Models

View all →

Name

5 models

Size

Context

Input

granite3.2-vision:2b

3.6GB · 128K context window · Text, Image · 7 months ago

granite3.2-vision:2b

3.6GB

128K

Text, Image

Readme

Granite 3.2 Vision models

A compact and efficient vision-language model, specifically designed for visual document understanding, enabling automated content extraction from tables, charts, infographics, plots, diagrams, and more. The model was trained on a meticulously curated instruction-following dataset, comprising diverse public datasets and synthetic datasets tailored to support a wide range of document understanding and general image tasks. It was trained by fine-tuning a Granite large language model with both image and text modalities.

Running

ollama run ibm/granite3.2-vision

Learn more

Release Date: February 26th, 2025
License: Apache 2.0
https://www.ibm.com/granite