Sold by: Gigabits
Deployed on AWS
AWS Free Tier
Hardened image with security baselines applied at first boot. 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.
Overview
GigaOps AI Runtime Guard delivers a production-ready LocalAI deployment on Ubuntu 24 with integrated inference monitoring built by Gigabits.
Key Features:
- Model Health Monitoring: Periodic probes confirm LocalAI responds correctly.
- Resource Tracking: CPU, memory, and GPU utilization with historical trends.
- Auto-Restart: Detects crashed model processes and recovers automatically.
- Alert System: Notifications when resources exceed safe thresholds.
- Security Hardening: Firewall, SSH restrictions, and non-root execution.
- One-Command Diagnostics: gigaops ai-report for infrastructure and model health.
Ideal For: Teams running LocalAI for private AI inference who need monitoring and automatic recovery without cloud AI dependencies.
Highlights
- Model health monitoring for LocalAI on Ubuntu 24. Periodic probes confirm AI inference responds correctly. Auto-restart recovers crashed processes automatically.
- Resource tracking for CPU, memory, and GPU with alerts. Historical utilization trends. Security hardening with firewall and non-root model execution on first boot.
- One-command diagnostics for AI infrastructure health. Private AI inference on Ubuntu 24 LTS with built-in reliability and monitoring. No cloud AI dependencies required.
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 |
|---|---|
t2.micro Recommended | $0.21 |
t3.micro | $0.10 |
g4dn.metal | $3.35 |
m3.medium | $0.18 |
t2.nano | $0.05 |
t2.small | $0.90 |
c4.large | $0.17 |
m3.large | $0.13 |
m5ad.large | $0.15 |
m5n.large | $0.13 |
Dimensions summary
You pay by the hour for the software running on your chosen Amazon EC2 instance. Each dimension maps to one EC2 instance type, so pricing scales with the compute you select. Options span general-purpose, compute-optimized, memory-optimized, storage, and GPU or accelerator families in sizes from small shared instances up to bare-metal and multi-terabyte machines. Larger instances carry higher hourly rates. There is no upfront commitment; you are billed only for the hours each instance runs. Add AWS infrastructure charges separately. Pick the instance that matches your workload size and budget.
Top-of-mind questions for buyers
Each hourly rate covers the LocalAI software running on one EC2 instance of the type you pick. It does not include the underlying AWS compute, storage, or network charges. Those AWS infrastructure fees bill separately from Amazon. You pay both the software rate and the AWS resource cost.
The hourly software charge meters running time only. A fully stopped instance does not accrue the software fee. Stopped instances may still incur AWS storage charges for attached volumes, but those are separate from the software rate you see in the pricing table.
Each listed instance type is a separate hourly rate. Larger instances with more compute, memory, or GPU capacity carry higher rates. If you launch a different instance type, you pay that type's rate for the hours it runs. There is no upfront commitment tying you to one type.
cloudgigabits.com
Helpful?
Vendor refund policy
No refunds, please cancel at anytime
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
localai release 1
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.
All usage instructions on link: https://gigabits-logos.s3.us-east-1.amazonaws.com/Gigabits-Local+AI-Ubuntu+24.04.pdf
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:
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
Hardened image with security baselines applied at first boot. 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.
GuardrailsAI Pro delivers enterprise-grade infrastructure for AI risk mitigation in your AWS environment. Our solution provides real-time validation for LLM applications with high-performance ML-based guardrails, ensuring complete control and security within your existing AWS infrastructure.
IBM Granite Guardian 3.2 5B is a streamlined AI model designed to detect risks in prompts and responses, enhancing safety and efficiency.
Kriv AI deploys and tunes Amazon Bedrock Guardrails for regulated industries including healthcare, life sciences, and financial services. Provides denied-topics taxonomies, PHI/PII blocklists, content/word/sensitive-data filters using Amazon Comprehend Medical and Amazon Macie, grounding checks, and fairness filters (disparate-impact detection and protected-class proxy scanning). Implements jailbreak and prompt-injection defenses aligned with OWASP Top 10 for LLM Applications (2024/2025). Supports A/B testing vs baseline with precision, recall, F1, and FPR tracking, with compliance mapping to SOC 2 Type II, HIPAA §164.308/312/316, and NIST AI RMF. Integrates with Amazon Bedrock Agents, Claude Agent SDK, and MCP servers. EDP-eligible — counts toward your AWS Enterprise Discount Program commitment (up to 25%). Contact info@kriv.ai for private offer scoping. Pricing tiers: $35K / $65K / $95K + $15K Denied-Topic Suite. AWS Select + Databricks + Anthropic CPN (April 9, 2026).
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.