skills.rest
2nth-ai
2nth-aiOFFICIAL
Explore all skills by this author →
GitHub

tech/ollama/deployment

Deploy Ollama AI service on Docker, Kubernetes, Linux, and Apple Silicon with GPU support.

1|Updated Apr 1, 2026
Search Tags:#deployment#Docker#Kubernetes#Ollama#GPU#Linux#Apple Silicon
One-click install
npx skills add https://github.com/2nth-ai/skills --skill tech-ollama-deployment
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: tech/ollama/deployment
Source: https://github.com/2nth-ai/skills/tree/main/tech/ollama/deployment
Command: npx skills add https://github.com/2nth-ai/skills --skill tech-ollama-deployment

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires Docker, Kubernetes, systemd, Metal, ROCm, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill facilitates the deployment of Ollama across various environments, including Docker, Kubernetes, Linux services, and Apple Silicon, with emphasis on GPU capabilities.

Core Features & Use Cases

  • Cross-Platform Deployment: Simplifies deployment on Docker, Kubernetes, systemd services, and Apple Silicon.
  • GPU Support: Optimizes performance with GPU passthrough for Docker and Kubernetes, and Metal GPU support for Apple Silicon.
  • Use Case: For an organization looking to deploy a scalable Ollama instance, this skill provides a comprehensive set of instructions to deploy Ollama with the necessary configurations for each platform.

Quick Start

Deploy Ollama with GPU support on your Linux machine using the provided deployment script.

Frequently Asked Questions about tech/ollama/deployment

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I deploy Ollama with GPU support on Kubernetes?▼

To deploy Ollama on Kubernetes with GPU support, you must configure GPU passthrough within your cluster resources. This Skill provides the necessary scripts and configurations to ensure the Ollama AI service utilizes available GPU capabilities for optimized production execution.

Can I run Ollama on Apple Silicon using Metal GPU acceleration?▼

Yes, you can run Ollama on Apple Silicon utilizing Metal GPU support for hardware acceleration. This Skill includes specific deployment configurations that enable the Ollama service to leverage Metal capabilities for optimized performance on Apple platforms.

Do I need Docker and specific GPU drivers to deploy Ollama?▼

Yes, deploying Ollama with GPU optimization requires Docker and appropriate GPU drivers installed on your host system. This Skill depends on these environments to facilitate cross-platform deployment and ensure the Ollama service can access GPU resources.

What is the best way to run Ollama as a Linux systemd service?▼

The best way to run Ollama as a Linux service is by configuring it through systemd for persistent background execution. This Skill provides the deployment references and scripts needed to establish Ollama as a reliable Linux service.

Does this Ollama deployment support ROCm for AMD GPUs?▼

Yes, this Ollama deployment supports ROCm to enable GPU acceleration for AMD hardware. The Skill incorporates ROCm dependencies alongside Docker and Kubernetes configurations to optimize the Ollama AI service across various GPU environments.

Related Skills

AmitabhainArunachalaAmitabhainArunachala
1

universal-inference-runtime

Run LLM inference across Ollama and llama.cpp backends with hot model swapping.

Community
Intermediate
haxlyshaxlys

istio-traffic-management

Configure Istio VirtualService, DestinationRule, Gateway, and ServiceEntry for service mesh routing.

Community
Advanced
pluginagentmarketplacepluginagentmarketplace
2

llm-basics

Explain transformer architecture, tokenization, and inference optimization for LLMs.

Community
Intermediate
masteryyhmasteryyh
7

devops

Automate multi-cloud deployment across Cloudflare, Docker, Google Cloud, and Kubernetes.

Community
Advanced