Explore 130K+ AI Models on FriendliAI's Models Page

We’re excited to launch our new models page, a central place where you can explore and use all the AI models available on our platform. This update makes it easier than ever to find the perfect model for your needs–whether you’re working on text, audio, video, image, or multimodal tasks–and deploy it with just a single click.

A Diverse Collection of Generative AI Models

FriendliAI offers diverse model support, including LoRA adapters, and fine-tuned, merged, and quantized models. Here’s a breakdown of the models available, as of March 20, 2025:

• Language Models: 131,293 models
• Audio Understanding: 62 models
• Image Understanding: 2,220 models
• Image Generation: 350 models
• Video Understanding: 272 models
• Total: 131,643 models

Furthermore, you can also deploy your custom models directly from Hugging Face with just one click. Check out our previous blog posts, “Deploy Models from Hugging Face to Friendli Endpoints” and “Deploy Multimodal Models from Hugging Face to FriendliAI with Ease” to learn more.

We are constantly adding new models to our supported list. If you don't see the specific model you need, you can submit a request here and we'll add it as soon as we can.

Seamless Integration with Friendli Endpoints

One of the most standout features of the new models page is the ability to view the list of endpoints for each model. This allows you to quickly identify and deploy the models you want, streamlining the process of deploying AI solutions.

Friendli Optimized Models

We’ve gone above and beyond to optimize some of the most popular models, delivering exceptional performance and quality through our cutting-edge inference acceleration technology. Experience the next level of performance with FriendliAI.

You can filter by “Optimized” to see these accelerated models, such as:

Company	Model
DeepSeek	DeepSeek-R1-Distill-Qwen-1.5B DeepSeek-R1-Distill-Qwen-32B DeepSeek-R1-Dilstill-Llama-8B DeepSeek-R1-Distill-Qwen-7B DeepSeek-R1-Distill-Llama-70B DeepSeek-R1-Distill-Qwen-14B
Meta	Llama-3.3-70B-Instruct Llama-3.2-3B-Instruct Llama-3.1-8B-Instruct Llama-3.1-70B-Instruct
Microsoft	phi-4 Phi-3.5-mini-instruct
Mistral	Mistral-7B-Instruct-v0.3
NVIDIA	Llama-3.1-Nemotron-70B-Instruct
Qwen	Qwen2.5-Coder-32B-Instruct Qwen2.5-72B-Instruct QwQ-32B-Preview

FriendliAI is at the forefront of fast, efficient, and reliable generative AI inference-time scaling. Recognized as the world’s fastest GPU-based API provider by Artificial Analysis, FriendliAI enables businesses to deploy and serve custom AI models with minimal latency and reduced cost.

By leveraging FriendliAI's technology, companies can harness the power of AI to drive innovation and growth. If you'd like to optimize and deploy your own models for superior performance, don't hesitate to reach out to us. We're here to help you take your services to new heights! Check out our previous blog post “Compress Generative AI Models with Friendli Model Optimizer” to learn more.

Start Exploring Today

Visit our models page to explore our ever-growing list of over 130,000 AI models and revolutionize your projects. Find the perfect model to elevate your work.

Stay tuned for more updates as we continue to expand and enhance our platform! Can't find the model you need? Submit a request here.