![TitanML's profile picture](https://cdn-avatars.huggingface.co/v1/production/uploads/66281f4e8bfc90408a895226/JjTVmUOUhDrHs-jEe41ek.jpeg)
TitanML
AI & ML interests
Quantized Foundation Models
🚀 Effortless and Secure Deployment of Enterprise RAG for Regulated Industries
TitanML enables organizations in regulated industries to effortlessly and efficiently deploy Enterprise RAG. Our TitanML Enterprise Inference Stack makes building, deploying, and scaling Enterprise RAG applications in secure environments a breeze.
TitanML: The Fastest Way to Enterprise RAG Inference
Our TitanML Enterprise Inference Stack offers:
- Lightning-fast local inference
- Efficient batching support
- Multi-GPU inference capabilities
- INT4 quantization for reduced memory footprint
- And much more!
🌐 Quantized Open-Source Models
We have quantized over 50 popular open-source foundation models, making them more accessible and efficient for the enterprise. Some of our featured models include:
- TitanML/opt-125m-AWQ-4bit
- TitanML/Llama3-OpenBioLLM-70B-AWQ-4bit
- TitanML/Meta-Llama-3-8B-AWQ-4bit
- TitanML/Meta-Llama-3-8B-Instruct-AWQ-4bit
- TitanML/llava-v1.6-mistral-7b
- TitanML/tiny-mistral-embedder
- TitanML/jina-v2-base-en-embed
- TitanML/llama2-70b-base-4bit-AWQ
- TitanML/llama2-13b-base-4bit-AWQ
- TitanML/llama2-7b-base-4bit-AWQ
- And many more!
Explore our full collection of quantized models and empower your organization with state-of-the-art Gen AI capabilities.
🔒 Secure and Compliant
We understand the importance of security and compliance in regulated industries. TitanML provides the tools and libraries to ensure your AI applications meet the strictest security and compliance requirements.
🤝 Connect with Us
💬 Get in Touch
Have questions or want to learn more? We'd love to hear from you!
📧 Email us at [email protected]
spaces
1
models
33
![](https://cdn-avatars.huggingface.co/v1/production/uploads/66281f4e8bfc90408a895226/JjTVmUOUhDrHs-jEe41ek.jpeg)
TitanML/InternVL2-Llama3-76B-AWQ
![](https://cdn-avatars.huggingface.co/v1/production/uploads/66281f4e8bfc90408a895226/JjTVmUOUhDrHs-jEe41ek.jpeg)
TitanML/dummy_model
![](https://cdn-avatars.huggingface.co/v1/production/uploads/66281f4e8bfc90408a895226/JjTVmUOUhDrHs-jEe41ek.jpeg)
TitanML/tiny-mixtral
![](https://cdn-avatars.huggingface.co/v1/production/uploads/66281f4e8bfc90408a895226/JjTVmUOUhDrHs-jEe41ek.jpeg)
TitanML/tiny-random-gemma2
![](https://cdn-avatars.huggingface.co/v1/production/uploads/66281f4e8bfc90408a895226/JjTVmUOUhDrHs-jEe41ek.jpeg)
TitanML/tiny-mixtral-AWQ-4bit
![](https://cdn-avatars.huggingface.co/v1/production/uploads/66281f4e8bfc90408a895226/JjTVmUOUhDrHs-jEe41ek.jpeg)
TitanML/opt-125m
![](https://cdn-avatars.huggingface.co/v1/production/uploads/66281f4e8bfc90408a895226/JjTVmUOUhDrHs-jEe41ek.jpeg)
TitanML/tinyllava-1.1b-v0.1
![](https://cdn-avatars.huggingface.co/v1/production/uploads/66281f4e8bfc90408a895226/JjTVmUOUhDrHs-jEe41ek.jpeg)
TitanML/TinyLlama-1.1B-step-50K-105b-AWQ-4bit
![](https://cdn-avatars.huggingface.co/v1/production/uploads/66281f4e8bfc90408a895226/JjTVmUOUhDrHs-jEe41ek.jpeg)
TitanML/Meta-Llama-3-8B-Instruct-Marlin-4bit
![](https://cdn-avatars.huggingface.co/v1/production/uploads/66281f4e8bfc90408a895226/JjTVmUOUhDrHs-jEe41ek.jpeg)