meta

Llama-3.2-11B-Vision-Instruct

llama

Open multimodal Llama model for image understanding, captioning, and visual QA

Tool CallingAttachmentsOpen Weights

Context Window

128K

Max Output

4K

Temperature

Yes

Open Weights

Yes

Knowledge Cutoff

2023-12

Released

2024-09-25

Last Updated

2024-09-25

Modalities

Input:TextImage
→
Output:Text

Available Providers (2)

ProviderInput /1MOutput /1MCache Read /1MCache Write /1MReasoningStatus
InferenceInferenceRp 999Rp 999———Deprecated
NvidiaNvidiaGratisGratis————