tech/ollama/models
OfficialOptimize Ollama model selection and management for AI tasks.
Author2nth-ai
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill streamlines the selection and management of Ollama models, addressing the trade-offs between model size, quality, and speed, and helps in managing VRAM budgets and using embedding models locally.
Core Features & Use Cases
- Model Selection: Choose the right open-weight model based on size, quality, and speed.
- Model Retrieval: Pull models from the Ollama library or Hugging Face GGUF.
- Quantisation Levels: Understand and apply quantisation levels (e.g., Q4_K_M, Q8_0, fp16).
- VRAM Management: Determine which models fit on which GPUs.
- Local Embedding Models: Use embedding models like nomic-embed-text and mxbai-embed-large locally.
- Use Case: When you need to select a model for a specific task, such as coding or reasoning, and want to ensure it fits within your VRAM constraints.
Quick Start
Use the tech/ollama/models skill to pull a model suitable for coding tasks, like 'qwen2.5-coder:7b'.
Dependency Matrix
Required Modules
None requiredComponents
scriptsreferences
💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: tech/ollama/models Download link: https://github.com/2nth-ai/skills/archive/main.zip#tech-ollama-models Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 620,000+ vetted skills library on demand.