\n
ollama run llama3.2-vision<\/code><\/pre>\n \n Copy<\/button>\n <\/amp-iframe>\n <\/div>\n\n\n\n3. Install the 90B Version<\/h3>\n\n\n\n To install the 90B model (55GB), use this command:\n\n\n\n
\n
ollama run llama3.2-vision:90b<\/code><\/pre>\n \n Copy<\/button>\n <\/amp-iframe>\n <\/div>\n\n\n\n4. Verify the Installation<\/h3>\n\n\n\n Once the installation is complete, you will see the >>><\/code> prompt. This indicates that the model is ready for interaction.\n\n\n\nWhat to Do:<\/strong>\n\n\n\n\nAt the >>><\/code> prompt, type a question or a command to verify that the model is functioning properly.<\/li>\n\n\n\nExample Interaction<\/strong>:<\/li>\n<\/ul>\n\n\n\n\n
Describe the contents of this image: \/path\/to\/your\/image.jpg.<\/code><\/pre>\n \n Copy<\/button>\n <\/amp-iframe>\n <\/div>\n\n\n\nSupported Languages<\/h2>\n\n\n\n\nFor text-only tasks<\/strong>, Llama 3.2 Vision supports: English<\/strong>, German<\/strong>, French<\/strong>, Italian<\/strong>, Portuguese<\/strong>, Hindi<\/strong>, Spanish<\/strong>, and Thai<\/strong>.<\/li>\n\n\n\nFor image+text applications<\/strong>, only English<\/strong> is supported.<\/li>\n<\/ul>\n\n\n\nUse Cases of Llama 3.2 Vision<\/h2>\n\n\n\n Here are some practical applications of Llama 3.2 Vision:\n\n\n\n
1. Image Captioning<\/strong><\/h3>\n\n\n\n\nGenerate descriptive text for images, which is helpful for accessibility and content management.<\/li>\n\n\n\n Example Use:<\/strong> Automatically caption photos for a photography blog.<\/li>\n<\/ul>\n\n\n\n2. Image Question Answering<\/strong><\/h3>\n\n\n\n\nAnswer questions about images for educational or analytical purposes.<\/li>\n\n\n\n Example Use:<\/strong> Answering \u201cHow many people are in this picture?\u201d for an event analysis.<\/li>\n<\/ul>\n\n\n\n3. Visual Reasoning<\/strong><\/h3>\n\n\n\n\nUnderstand and analyze the relationships between objects in images.<\/li>\n\n\n\n Example Use:<\/strong> Determining if there is enough space to park a car in an image.<\/li>\n<\/ul>\n\n\n\n4. Object Recognition<\/strong><\/h3>\n\n\n\n\nIdentify and classify objects within an image.<\/li>\n\n\n\n Example Use:<\/strong> Detecting various items in a supermarket shelf image for inventory tracking.<\/li>\n<\/ul>\n\n\n\n5. Scene Understanding<\/strong><\/h3>\n\n\n\n\nProvide contextual information about a scene, such as whether it\u2019s indoors or outdoors.<\/li>\n\n\n\n Example Use:<\/strong> Identifying a living room setting in a smart home system.<\/li>\n<\/ul>\n\n\n\nExample Code for Using Llama 3.2 Vision<\/h2>\n\n\n\n1. Python Example<\/h3>\n\n\n\n\n
import ollama\n\nresponse = ollama.chat(\n model='llama3.2-vision',\n messages=[{\n 'role': 'user',\n 'content': 'How many animals are in this image?',\n 'images': ['path\/to\/your\/image.jpg'] # Replace with your image path\n }]\n)\n\nprint(response)<\/code><\/pre>\n \n Copy<\/button>\n <\/amp-iframe>\n <\/div>\n\n\n\n2. JavaScript Example<\/h3>\n\n\n\n\n
import ollama from 'ollama';\n\nconst response = await ollama.chat({\n model: 'llama3.2-vision',\n messages: [{\n role: 'user',\n content: 'What is the person in this image doing?',\n images: ['path\/to\/your\/image.jpg'] \/\/ Replace with your image path\n }]\n});\n\nconsole.log(response);<\/code><\/pre>\n \n Copy<\/button>\n <\/amp-iframe>\n <\/div>\n\n\n\n3. cURL Example<\/h3>\n\n\n\n\n
curl http:\/\/localhost:11434\/api\/chat -d '{\n "model": "llama3.2-vision",\n "messages": [\n {\n "role": "user",\n "content": "What is in this image?",\n "images": ["<base64-encoded image data>"]\n }\n ]\n}'<\/code><\/pre>\n \n Copy<\/button>\n <\/amp-iframe>\n <\/div>\n\n\n\nNote:<\/strong> For the cURL example, replace \"<base64-encoded image data>\"<\/code> with the actual base64-encoded string of your image.\n\n\n\nThis tutorial should help you get Llama 3.2 Vision up and running on your Mac, and you can start exploring its diverse capabilities across image and text tasks. Happy experimenting!\n","protected":false},"excerpt":{"rendered":"
Llama 3.2 Vision is a collection of advanced, instruction-tuned, multimodal large language models (LLMs) optimized for image reasoning, image captioning, and more. This guide will […]<\/p>\n","protected":false},"author":1,"featured_media":1417,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[24],"tags":[252,17,21],"class_list":["post-1408","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-artificial-intelligence","tag-llama-3-2-vision","tag-mac-m1-m2-m3","tag-ollama"],"amp_enabled":true,"_links":{"self":[{"href":"https:\/\/zahiralam.com\/blog\/wp-json\/wp\/v2\/posts\/1408","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/zahiralam.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/zahiralam.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/zahiralam.com\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/zahiralam.com\/blog\/wp-json\/wp\/v2\/comments?post=1408"}],"version-history":[{"count":5,"href":"https:\/\/zahiralam.com\/blog\/wp-json\/wp\/v2\/posts\/1408\/revisions"}],"predecessor-version":[{"id":1418,"href":"https:\/\/zahiralam.com\/blog\/wp-json\/wp\/v2\/posts\/1408\/revisions\/1418"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/zahiralam.com\/blog\/wp-json\/wp\/v2\/media\/1417"}],"wp:attachment":[{"href":"https:\/\/zahiralam.com\/blog\/wp-json\/wp\/v2\/media?parent=1408"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/zahiralam.com\/blog\/wp-json\/wp\/v2\/categories?post=1408"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/zahiralam.com\/blog\/wp-json\/wp\/v2\/tags?post=1408"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}