Sold by: Gigabits
Deployed on AWS
AWS Free Tier
This is a repackaged open source software product wherein additional charges apply for custom operational agents. Includes GPU and memory alerts, model serve health checks, automatic restart on failure, and resource tracking. Run AI inference with built-in reliability.
Overview
GigaOps AI Runtime Guard provides production-grade reliability for DeepSeek-R1 on Ubuntu 24. Built by Gigabits, it monitors and protects AI inference workloads.
Key Features:
- GPU/Memory Alerts: Real-time notifications when GPU memory, system RAM, or temperature exceed thresholds.
- Model Serve Health: Periodic inference probes confirm the model is responding correctly.
- Auto-Restart: Detects crashed or hung model processes and restarts with cooldown logic.
- Resource Tracking: Historical GPU utilization, memory usage, and inference throughput.
- Security Hardening: Firewall rules, SSH key-only auth, and non-root model execution by default.
- One-Command Diagnostics: Run gigaops ai-report for infrastructure and model health.
Ideal For: Teams deploying DeepSeek-R1 for AI inference who need automated recovery and GPU monitoring.
Highlights
- GPU and memory monitoring for DeepSeek-R1 on Ubuntu 24. Real-time alerts when GPU memory, system RAM, or temperature exceed safe thresholds for AI inference workloads.
- Model serve health checks confirm DeepSeek-R1 responds correctly. Auto-restart recovers crashed or hung model processes with cooldown logic. Resource tracking shows historical utilization.
- DeepSeek-R1 on Ubuntu 24 deployed with firewall rules, SSH key-only auth, and non-root execution. One-command diagnostics with gigaops ai-report for AI infrastructure health.
Details
Sold by
Delivery method
Delivery option
64-bit (x86) Amazon Machine Image (AMI)
Latest version
Operating system
Ubuntu 24
Deployed on AWS
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
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
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.
If you are an AWS Free Tier customer with a free plan, you are eligible to subscribe to this offer. You can use free credits to cover the cost of eligible AWS infrastructure. See AWS Free Tier for more details. If you created an AWS account before July 15th, 2025, and qualify for the Legacy AWS Free Tier, Amazon EC2 charges for Micro instances are free for up to 750 hours per month. See Legacy AWS Free Tier for more details.
Dimension | Cost/hour |
|---|---|
t3.small Recommended | $0.09 |
t2.micro | $0.21 |
t3.micro | $0.10 |
g4ad.xlarge | $0.27 |
g4dn.xlarge | $0.27 |
g4dn.2xlarge | $0.55 |
g4ad.4xlarge | $1.11 |
g4dn.4xlarge | $1.11 |
g4ad.8xlarge | $2.23 |
g4dn.8xlarge | $2.23 |
Dimensions summary
You pay by the hour for the EC2 instance type you run this software on. Each dimension maps to one AWS instance size, so pricing scales with the compute, memory, GPU, or storage capacity you select. Smaller general-purpose instances cost less per hour, while GPU, memory-optimized, and bare-metal instances carry higher hourly rates. Compute-optimized, memory-optimized, storage-optimized, accelerated GPU, and inference instance families are all supported. You control cost by choosing an instance that fits your workload. Charges accrue only while an instance runs, with no upfront commitment.
Top-of-mind questions for buyers
Each hourly unit covers one running EC2 instance of the type you select. The rate combines the software license and covers a single instance for each hour it runs. The instance size you pick sets its compute, memory, GPU, and storage capacity, which determines your hourly rate.
Software charges accrue only while an instance runs. If you stop an instance, the hourly software charge stops. Stopped instances may still incur separate AWS storage fees for attached volumes, but the software license meters running hours only. There is no upfront commitment.
Choose an instance type that matches your workload. Smaller general-purpose instances carry lower hourly rates. GPU, memory-optimized, storage-optimized, and bare-metal instances carry higher rates for heavier work. You pay per hour for one instance at a time, so running fewer or smaller instances reduces cost.
cloudgigabits.com
Helpful?
Vendor refund policy
No refunds, cancel at any time
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
Updated with Gigabits Ops
Additional details
Usage instructions
ssh to the instance public IP and login as 'ubuntu' user using the key specified at launch time. Use 'sudo su -' in order to get a root prompt. To use the Gigabits Ops Agent, follow instructions here: https://gigabits-logos.s3.us-east-1.amazonaws.com/gigabits-ops-agent-usage-instructions.pdf
For more information please visit the links below:
All instructions: https://gigabits-logos.s3.us-east-1.amazonaws.com/Gigabits-Deepseek-r1.pdf
Connect to your Linux instance from Windows using PuTTY: https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/putty.html
Connect to your Linux instance using SSH: https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/AccessingInstancesLinux.html
Support
Vendor support
please contact support@gigabitscloud.com for any inquiries
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
This is a repackaged open source software product wherein additional charges apply for custom operational agents. Includes model health monitoring, resource tracking, auto-restart on failure, and GPU/CPU alerts. Run local AI inference with built-in reliability.
PointGuard AI, a Validated Technology Partner of Databricks, significantly enhances the security and governance of AI projects on the Databricks platform. PointGuard AI's solutions provide guardrails and policy enforcement across the entire AI lifecycle, from data ingestion to model deployment. By combining Databricks' powerful data processing capabilities with PointGuard AI's robust security measures, organizations can accelerate their AI initiatives while maintaining a strong security posture, ensuring that sensitive data and AI models are protected from evolving threats.
Arcade.dev is the industry's first MCP runtime enabling AI to take secure, real-world actions. As the MCP runtime, Arcade is uniquely able to deliver secure agent authorization, high-accuracy tools, and centralized governance for multi-user AI agents at scale.
Tumeryk AI Trust Score™ Guardrails provide real-time security and governance for GenAI agents and applications by enforcing jailbreak detection, bias monitoring, and content moderation. Integrated with tools like Wiz, Tumeryk also discovers Shadow AI and scores its risk, ensuring safe and compliant AI adoption.
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.