llama3.2-vision

2.1M 4 days ago

Llama 3.2 Vision is a collection of instruction-tuned image reasoning generative models in 11B and 90B sizes.

vision 11b 90b

9 models

llama3.2-vision:latest
684232d97d29 • 8.1GB • 128K context window •
Text, Image input • 4 days ago
llama3.2-vision:11b latest
684232d97d29 • 8.1GB • 128K context window •
Text, Image input • 4 days ago
llama3.2-vision:90b
d7b8e0f6c763 • 56GB • 128K context window •
Text, Image input • 4 days ago
llama3.2-vision:11b-instruct-q4_K_M
684232d97d29 • 8.1GB • 128K context window •
Text, Image input • 4 days ago
llama3.2-vision:11b-instruct-q8_0
85ac1e2f7e80 • 12GB • 128K context window •
Text, Image input • 4 days ago
llama3.2-vision:11b-instruct-fp16
ad46bd2e98f2 • 21GB • 128K context window •
Text, Image input • 4 days ago
llama3.2-vision:90b-instruct-q4_K_M
d7b8e0f6c763 • 56GB • 128K context window •
Text, Image input • 4 days ago
llama3.2-vision:90b-instruct-q8_0
85d17bee22d0 • 96GB • 128K context window •
Text, Image input • 4 days ago
llama3.2-vision:90b-instruct-fp16
6332e6d39cde • 177GB • 128K context window •
Text, Image input • 4 days ago