Sold by: MultiCortex
Deployed on AWS
Free Trial
AWS Free Tier
Built on openSUSE Linux, this product provides private AI using the Phi-4 model with 14 billion parameters. MultiCortex HPC (High-Performance Computing) allows you to boost your AI's response quality. This is a plug-and-play, low-cost product with no token fees.
Overview
ABOUT PHI4:
Phi4 is a state of the art language model developed by Microsoft, standing out for its ability to perform complex reasoning, especially in areas like mathematics. With 14 billion parameters, Phi4 represents a significant advancement for Microsoft, delivering high-quality results in a relatively compact size.
Performance and Applications:
Phi4 outperforms comparable models in tasks related to mathematical reasoning, thanks to advancements in its training process and the use of high-quality curated data. Additionally, its efficiency allows it to be deployed in environments with limited computational resources, enabling local execution with reduced latency and lower operational cost.
Key Strengths of Phi4:
- High performance in mathematical reasoning. Outperforms larger models in math-related tasks due to its optimized training.
- Computational efficiency. Can run on local devices with lower operational costs and low latency.
- Optimized architecture. Decoder-only transformer model with 14 billion parameters and a 16,000 token context window.
- Advanced training. Uses high-quality synthetic data and a rigorous fine-tuning process for better instruction following.
- Enhanced safety and alignment. Incorporates modern techniques to ensure safer and more reliable responses.
Highlights
- Boost your private AI system with MultiCortex HPC and leave the thousands of AI updates to us
- Enjoy full technical compliance with complete data control in the hands of your company
- No token fees, enhanced performance, and lower consumption of computing resources
Details
Sold by
Delivery method
Delivery option
64-bit (x86) Amazon Machine Image (AMI)
Latest version
Operating system
AmazonLinux Leap 15.6
Deployed on AWS
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Free trial
Try this product free for 31 days according to the free trial terms set by the vendor. Usage-based pricing is in effect for usage beyond the free trial terms. Your free trial gets automatically converted to a paid subscription when the trial ends, but may be canceled any time before that.
Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Cost/hour |
|---|---|
g4dn.xlarge Recommended | $0.50 |
t3.micro AWS Free Tier | $0.50 |
t2.micro AWS Free Tier | $0.50 |
c6a.48xlarge | $0.50 |
m6i.2xlarge | $0.50 |
x2iedn.2xlarge | $0.50 |
c5a.16xlarge | $0.50 |
m5zn.6xlarge | $0.50 |
i7ie.xlarge | $0.50 |
c6id.metal | $0.50 |
Vendor refund policy
If you need to request a refund for software sold by Amazon Web Services, LLC, please contact AWS Customer Service.
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
64-bit (x86) Amazon Machine Image (AMI)
Amazon Machine Image (AMI)
An AMI is a virtual image that provides the information required to launch an instance. Amazon EC2 (Elastic Compute Cloud) instances are virtual servers on which you can run your applications and workloads, offering varying combinations of CPU, memory, storage, and networking resources. You can launch as many instances from as many different AMIs as you need.
Version release notes
Phi4 model and all packages installed automatically.
Additional details
Usage instructions
Additional details Usage instructions <br><br> To use the product, follow these steps: 1. Open a web browser and go to the application at the following address: https://<EC2_Instance_Public_DNS>/index.html. 2. Log in using the credentials below: - Username: ec2-user - Password: the instance_id of your instance. After launching an EC2 instance, wait about 15 minutes for the system to complete the automatic configuration and download of the LLM template. After this time, you can access the chat interface by typing the instance's IP address followed by port 7000 into your browser. For example: http://10.21.103:7000 .
Support
Vendor support
The support service called MultiCortex, developed based on the openSUSE operating system, aims to provide the necessary resources for the efficient execution of AI models that are always up to date and aligned with the latest technological innovations in the area, offering a robust and secure environment for the development and application of AI-based solutions.
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
Gemma 3 12b Boosted by openSUSE MultiCortex HPC
By MultiCortex
Built on openSUSE Linux, this product provides private AI using the Gemma 3 model with 12 billion parameters. MultiCortex HPC (High-Performance Computing) allows you to boost your AI's response quality. This is a plug-and-play, low-cost product with no token fees.
Gemma 3 1b Boosted by openSUSE MultiCortex HPC
By MultiCortex
This product has charges associated with it for support from the seller. Built on openSUSE Linux, this product provides private AI using the Gemma 3 model with 1 billion parameters. MultiCortex HPC (High-Performance Computing) allows you to boost your AI's response quality. This is a plug-and-play, low-cost product with no token fees.
This is a repackaged software product wherein additional charges apply for OpenSUSE, with additional fees for technical support and maintenance provided by MultiCortex. This system is an advanced service dedicated to booster the performance of the Llama CPP inference engine, optimize the processing of accelerators available on the market, such as NPU (Neural Processing Unit), GPU (Graphics Processing Unit), and CPU (Central Processing Unit), and seamlessly connect with any open-source model (chat, video, images). The result is a user-friendly system that enables faster AI processing with reduced computational consumption. Undoubtedly, your best ally when it comes to developing AI solutions. This solution also includes supplier support for AI model updates and optimized versions for CPU, GPU, and NPU deployments.
Deepseek R-1 1.5b Boosted by openSUSE MultiCortex HPC
By MultiCortex
This product has charges associated with it for support from the seller. Built on openSUSE Linux, this product provides private AI using the Deepseek model with 1.5 billion parameters. MultiCortex HPC (High-Performance Computing) allows you to boost your AI's response quality. This is a plug-and-play, low-cost product with no token fees.
Customer reviews
No customer reviews yet
Be the first to write a review for this product.