LLM ReferenceLLM Reference

Llama 3.2 11B Vision

Open Source

About

Multimodal 11B parameter model balancing capability and computational efficiency

Capabilities

VisionMultimodalReasoningFunction CallingTool UseStructured OutputsCode Execution

Providers(1)

ProviderInput (per 1M)Output (per 1M)Type
AWS Bedrock$0.2$0.27Serverless

Benchmark Scores(2)

BenchmarkScoreVersionSource
Massive Multi-discipline Multimodal Understanding50.7https://mmmu-benchmark.github.io/
MMLU PRO46.4https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro

Rankings

Specifications

FamilyLlama 3.2
Released2024-09-25
Parameters10.6B
Context128K
ArchitectureDecoder Only
Knowledge cutoff2024-03
Specializationgeneral
Trainingfinetuning

Created by

Large-scale open-source AI for social technologies.

Menlo Park, California, United States
Founded 2013
Website

Providers(1)