- November 20, 2024
- 2 min read
Llama 3.2 11B Vision Model Available on Friendli Serverless Endpoints for Multi-Modal Support

We are thrilled to announce that Friendli Serverless Endpoints now supports the latest additions to Meta's Llama collection. Llama 3.2 models open up a world of possibilities for developers, enabling the creation of sophisticated multi-component AI systems that combine models, modalities, and external tools to deliver advanced real-world AI solutions.
Llama 3.2: Enhancing Modular AI Workflows
The release of Llama 3.2 11B Vision and Llama 3.2 90B Vision models brings a range of text-only and multimodal models designed to enhance modular AI workflows. These models provide deep customization options, allowing developers to tailor solutions and accelerate specific tasks in compound AI systems.
Multi-Modal Model Use Cases
Multimodal models like Llama 3.2 11B Vision and 90B Vision offer exciting possibilities across various domains:
- Visual Question Answering: These models can analyze images and answer questions about their content, making them ideal for applications in e-commerce, education, and accessibility.
- Document Analysis: The models excel at understanding complex documents, including charts and graphs, making them valuable for business intelligence and data analysis tasks.
- Image Captioning: Llama 3.2 can generate descriptive captions for images, useful in content management systems and social media platforms.
- Visual Grounding: The models can identify specific objects or areas within an image based on natural language descriptions, enhancing interactive applications and search functionalities.
Spotlight on Llama 3.2 11B Vision
The Llama 3.2 11B Vision model is a powerful AI that combines visual recognition with language understanding. Here are some key characteristics:
- Multimodal Capabilities: It can process both text and images as inputs, enabling a wide range of applications.
- High Performance: The model achieves impressive accuracy on various benchmarks, including 66.8% on VQAv2 and 73.1% on Text VQA.
- Efficient Architecture: Built on top of the Llama 3.1 text-only model, it uses a separately trained vision adapter for optimal performance.
- Extended Context Length: Supports up to 128K tokens, allowing for in-depth understanding and context retention.
Getting Started with Llama 3.2 11B Vision
To try out the Llama 3.2 11B Vision model on Friendli Serverless Endpoints:
- Sign in to the Friendli Suite
- Choose Friendli Serverless Endpoints
- Select the Llama 3.2 11B Vision model from the models list
- Run your query!
Real-World Applications
To demonstrate the capabilities of Llama 3.2 11B Vision, we've included two impressive examples:
- Creating a 30-second TV commercial: The model can analyze an image and generate creative concepts for a short commercial, showcasing its ability to understand visual content and produce relevant, engaging text.

- Inferring characteristics and cultural background from a poster image: Llama 3.2 11B Vision can extract detailed information from visual media, providing insights into the subjects, themes, and cultural context depicted in images.

Get Started Today!
Don't miss this opportunity to explore the cutting-edge capabilities of Llama 3.2 models. Sign up for Friendli Serverless Endpoints and start building the next generation of AI-powered applications today!
Written by
FriendliAI Tech & Research
Share
General FAQ
What is FriendliAI?
FriendliAI is the Frontier Inference Cloud for Agents, delivering high throughput, low latency, and reliability at scale for agentic workloads. Through vertically optimized inference infrastructure, it delivers 2–5× faster output token speed and a 99.99% uptime SLA for high-volume production traffic.
How does FriendliAI reduce inference costs?
FriendliAI reduces inference costs through higher GPU utilization and optimized inference performance. FriendliAI's patented continuous batching technique, along with quantization, speculative decoding, KV cache offloading, multi-LoRA serving, and autoscaling, helps you serve more tokens with fewer GPUs, lowering your infrastructure costs without sacrificing performance.
Why should I choose FriendliAI over other inference providers?
FriendliAI is built for production AI agents, combining speed, reliability, and efficiency at scale. It delivers low-latency streaming, reliable long-context inference, and robust tool calling without compromising stability. According to independent OpenRouter benchmarks, FriendliAI consistently ranks among the top providers for throughput, latency, and reliability across leading open-weight models. See why customers choose FriendliAI
Which open-weight models does FriendliAI support?
Run today’s frontier open-weight models—including GLM, MiniMax, Kimi, DeepSeek, Qwen, Gemma, and more—with a simple API call. FriendliAI Model API gives you instant access to the latest models with optimized inference performance for production workloads. Explore models and pricing
How do I get started?
Getting started takes just a few minutes. [1] Sign up for FriendliAI, [2] Generate your API key, and [3] Make your first inference request with frontier open-weight models.
Still have questions?
If you want a customized solution for that key issue that is slowing your growth, support@friendli.ai or click Talk to an engineer — our engineers (not a bot) will reply within one business day.

