llama-3.2-90b-vision-instruct

Name: llama-3.2-90b-vision-instruct
Author: NVIDIA

llama3.290B

Context

131K

Max output

131K

Capabilities

Show unsupported (5)

Reasoning & Interaction

Tool Calling

Infrastructure

Streaming

Fine-tuning

ProviderNVIDIA

Licensellama3.2

Status—

Typechat

Input modalitiestext

Output modalitiestext

Open weightYes

Parameters90B

Architecture—

Context window131K tokens

Max input—

Max output131K tokens

Reasoning tokens—

Knowledge cutoff2023-12

Release date2024-09-19

Sourceofficial

Function Callingfunction_calling

Call external functions and APIs

Model	Caps	Perf	Speed	Context	Max out
llama-3.2-11b-vision-instruct	TSF	—	—	131K	131K
llama-3.2-1b-instruct	TSF	—	—	131K	131K
llama-3.2-3b-instruct	TSF	—	—	131K	131K
llama-3.2-90b-vision-instruct	TSF	—	—	131K	131K
llama-3.2-nemoretriever-1b-vlm-embed-v1	—	—	—	—	—
llama-3.2-nemoretriever-300m-embed-v1	—	—	—	—	—
llama-3.2-nv-embedqa-1b-v1	—	—	—	—	—
llama-3.2-nv-embedqa-1b-v2	—	—	—	—	—

GET/v1/models/nvidia/meta/llama-3.2-90b-vision-instruct

Changes · 3 entries

meta/llama-3.2-90b-vision-instructupdateb301ebeMar 23, 2026, 11:47 PM

modalitiesinput["text"]output["text"]

meta/llama-3.2-90b-vision-instructupdate2b100acMar 23, 2026, 05:30 AM

model_typechat

parameters90

tools["function_calling"]

meta/llama-3.2-90b-vision-instructcreate7f5c66fMar 21, 2026, 05:16 AM