Llama-3.2-90B-Vision-Instruct by Nvidia | AI model information

Loading models

Subscribe

Follow catalog updates and new guides

Open RSS feed Medium guides

RSS covers catalog changes. Medium covers how-to guides and write-ups.

Llama-3.2-90B-Vision-Instruct by Nvidia | AI model information

$10 off Synthetic - fastest OpenCode provider$10 off Synthetic - the fastest Kimi K2.6 and GLM 5.1 provider Discuss

Model details

Llama-3.2-90B-Vision-Instruct

Loading model overview

Nvidiameta/llama-3.2-90b-vision-instructllama

Open provider page Provider docs

Quick Info

Provider: Nvidia
Model key: meta/llama-3.2-90b-vision-instruct
Release date: Sep 25, 2024
Last updated: Sep 25, 2024

Cost

A provider subscription or plan supersedes token-based pricing for this model.

Limits

Output tokens: 8,192 tokens
Context window: 128,000 tokens

Latest news about Llama-3.2-90B-Vision-Instruct

Videos about Llama-3.2-90B-Vision-Instruct

Recent tweets and retweets from Nvidia

More models around Llama-3.2-90B-Vision-Instruct

7 providers

Llama 4 Scout 17B 16E Instruct

Currently listed through these providers:

Azure Azure Cognitive Services Cloudflare AI Gateway Cloudflare Workers AI GitHub Models +2 more

7 providers

Llama 4 Maverick 17B 128E Instruct FP8

Currently listed through these providers:

Abacus Azure Azure Cognitive Services GitHub Models Llama +2 more

5 providers

Llama 3.3 70B Instruct

Currently listed through these providers:

Berget.AI NanoGPT NovitaAI Regolo AI Vertex

5 providers

Llama 3.1 8B Instruct

Currently listed through these providers:

Nvidia Cloudflare AI Gateway Inference Regolo AI Scaleway

3 providers

Currently listed through these providers:

LLM Gateway NanoGPT OpenRouter

3 providers

Llama Guard 4 12B

Currently listed through these providers:

Nvidia Groq OpenRouter

3 providers

Llama 4 Maverick 17B 128E Instruct

Currently listed through these providers:

DigitalOcean IO.NET Vertex

3 providers

Llama Guard 3 8B

Currently listed through these providers:

Cloudflare AI Gateway Cloudflare Workers AI OpenRouter

2 providers

Llama 4 Maverick

Currently listed through these providers:

NanoGPT OpenRouter

2 providers

Currently listed through these providers:

NanoGPT Venice AI

2 providers

Llama 4 Maverick 17B Instruct

Currently listed through these providers:

Amazon Bedrock LLM Gateway

2 providers

Llama 4 Scout 17B

Currently listed through these providers:

Deep Infra Groq

Discuss this model

Powered byHyvor Talk

Add corrections, implementation notes, pricing changes, or usage caveats for other readers.

Knowledge cutoff

2023-12

Input modalities

Output modalities

Capabilities

Recent tweets and retweets from Nvidia

May 20, 2026, 12:16 AMUTC

At #GoogleIO, NVIDIA and @GoogleCloud are celebrating a milestone: More than 100,000 developers have joined our joint developer community in just one year, and the platform is expanding. In the past year, members have shipped RAG applications on GKE, built multi-agent…

May 19, 2026, 7:51 PMUTC

Excited to collaborate with @BlueYonder to help bring scalable AI innovation to supply chains worldwide. Looking forward to what’s next.

May 18, 2026, 11:51 PMUTC

Thanks @SpaceX and @elonmusk, excited for you to try out the NVIDIA Vera CPU 🎉

May 18, 2026, 9:58 PMUTC

Read more🔗 nvda.ws/42KhQgl

May 18, 2026, 9:56 PMUTC

NVIDIA’s Ian Buck hand-delivered the first-ever NVIDIA Vera CPUs to our partners @AnthropicAI, @OpenAI, @SpaceX, and @OracleCloud. 🎉 Vera is NVIDIA's first custom CPU, purpose-built for the age of agentic AI. This is just the beginning. The road to Vera-powered systems…