AI curriculum
Course outline for Local and Small Language Models
Hosted inference may not fit a workload's privacy or resource constraints. Evaluate small models and local runtimes to choose a workable deployment approach.
About Local and Small Language Models
Hosted inference may not fit a workload's privacy or resource constraints. Evaluate small models and local runtimes to choose a workable deployment approach.
Local and Small Language Models Course Objectives
- Compare local model formats and quantization options.
- Run or inspect a small-model inference workflow.
- Document hardware and privacy trade-offs.
Pre-requisites
- Basic command-line skills.
- Familiarity with language model inputs and outputs.
Lab Setup
- Computer with a terminal and a compatible local model runtime.
- Select a model that fits available memory; GPU access is optional.
- Use a supplied benchmark trace if local inference is impractical.
Detailed Course Outline
Proposed modulesModule 1: Local model choices
- Small language models
- Local inference
- Quantization
- Model formats
Practical outcome: Select a model format for a constrained machine.
Module 2: Deployment constraints
- Hardware considerations
- Ollama / llama.cpp-style ecosystems
- Privacy and deployment trade-offs
Practical outcome: Document a local runtime configuration and its limitations.
Practical exercise
- Compare two small-model configurations using a repeatable task and record resource use.
How we train
Contact us for full course details, including duration, delivery options and lab requirements.
Ask about exercises, instructor feedback and the prior knowledge you need. Tool-specific courses marked provisional may become modules in a broader course.
Discuss your learning goals