Course description and requirements
This proposed course develops practical knowledge of local ai deployment through guided instruction, supervised technical exercises, troubleshooting and documented projects.
Course code: AI-301 | Duration: 12 weeks | Workload: approximately 8–10 hours/week | Total: approximately 96–120 hours
Prerequisites: AI-101 and Linux fundamentals
Delivery: Planned online lessons, virtual laboratories, graded assessments and instructor feedback.
Status: In development; not open for enrollment.
Learning outcomes
- Explain the technical principles covered in the course
- Configure and troubleshoot relevant systems in an authorized lab
- Apply safe operational practices and document results
- Evaluate a working implementation against defined requirements
- Communicate findings in a professional technical report
Detailed 12-week teaching plan
Week 1: Local AI architectures
Lesson: Study the concepts, terminology, configuration steps, common failure modes and operational considerations for this topic.
Practical lab: Build or configure a relevant component in an isolated test environment; capture configuration details and verify the result.
Evidence: Submit a lab record containing the objective, steps, results, troubleshooting notes and a short reflection.
Week 2: Model formats
Lesson: Study the concepts, terminology, configuration steps, common failure modes and operational considerations for this topic.
Practical lab: Build or configure a relevant component in an isolated test environment; capture configuration details and verify the result.
Evidence: Submit a lab record containing the objective, steps, results, troubleshooting notes and a short reflection.
Week 3: Quantization
Lesson: Study the concepts, terminology, configuration steps, common failure modes and operational considerations for this topic.
Practical lab: Build or configure a relevant component in an isolated test environment; capture configuration details and verify the result.
Evidence: Submit a lab record containing the objective, steps, results, troubleshooting notes and a short reflection.
Week 4: CPU inference
Lesson: Study the concepts, terminology, configuration steps, common failure modes and operational considerations for this topic.
Practical lab: Build or configure a relevant component in an isolated test environment; capture configuration details and verify the result.
Evidence: Submit a lab record containing the objective, steps, results, troubleshooting notes and a short reflection.
Week 5: GPU inference
Lesson: Study the concepts, terminology, configuration steps, common failure modes and operational considerations for this topic.
Practical lab: Build or configure a relevant component in an isolated test environment; capture configuration details and verify the result.
Evidence: Submit a lab record containing the objective, steps, results, troubleshooting notes and a short reflection.
Week 6: Ollama installation
Lesson: Study the concepts, terminology, configuration steps, common failure modes and operational considerations for this topic.
Practical lab: Build or configure a relevant component in an isolated test environment; capture configuration details and verify the result.
Evidence: Submit a lab record containing the objective, steps, results, troubleshooting notes and a short reflection.
Week 7: Model management
Lesson: Study the concepts, terminology, configuration steps, common failure modes and operational considerations for this topic.
Practical lab: Build or configure a relevant component in an isolated test environment; capture configuration details and verify the result.
Evidence: Submit a lab record containing the objective, steps, results, troubleshooting notes and a short reflection.
Week 8: API fundamentals
Lesson: Study the concepts, terminology, configuration steps, common failure modes and operational considerations for this topic.
Practical lab: Build or configure a relevant component in an isolated test environment; capture configuration details and verify the result.
Evidence: Submit a lab record containing the objective, steps, results, troubleshooting notes and a short reflection.
Week 9: Prompt evaluation
Lesson: Study the concepts, terminology, configuration steps, common failure modes and operational considerations for this topic.
Practical lab: Build or configure a relevant component in an isolated test environment; capture configuration details and verify the result.
Evidence: Submit a lab record containing the objective, steps, results, troubleshooting notes and a short reflection.
Week 10: Privacy and security
Lesson: Study the concepts, terminology, configuration steps, common failure modes and operational considerations for this topic.
Practical lab: Build or configure a relevant component in an isolated test environment; capture configuration details and verify the result.
Evidence: Submit a lab record containing the objective, steps, results, troubleshooting notes and a short reflection.
Week 11: Performance measurement
Lesson: Study the concepts, terminology, configuration steps, common failure modes and operational considerations for this topic.
Practical lab: Build or configure a relevant component in an isolated test environment; capture configuration details and verify the result.
Evidence: Submit a lab record containing the objective, steps, results, troubleshooting notes and a short reflection.
Week 12: Local AI service project
Lesson: Study the concepts, terminology, configuration steps, common failure modes and operational considerations for this topic.
Practical lab: Build or configure a relevant component in an isolated test environment; capture configuration details and verify the result.
Evidence: Submit a lab record containing the objective, steps, results, troubleshooting notes and a short reflection.
Five graded practical assignments
Assignment 1 — Week 2: Model formats
Task: Complete a practical implementation or investigation related to model formats. Document the requirements, approach, evidence of operation, test results and any problems encountered.
Submission: Technical report, configuration evidence and supporting files where applicable.
Marking: Technical accuracy 40%, verification 25%, documentation 25%, safe practice 10%.
Assignment 2 — Week 4: CPU inference
Task: Complete a practical implementation or investigation related to cpu inference. Document the requirements, approach, evidence of operation, test results and any problems encountered.
Submission: Technical report, configuration evidence and supporting files where applicable.
Marking: Technical accuracy 40%, verification 25%, documentation 25%, safe practice 10%.
Assignment 3 — Week 5: GPU inference
Task: Complete a practical implementation or investigation related to gpu inference. Document the requirements, approach, evidence of operation, test results and any problems encountered.
Submission: Technical report, configuration evidence and supporting files where applicable.
Marking: Technical accuracy 40%, verification 25%, documentation 25%, safe practice 10%.
Assignment 4 — Week 8: API fundamentals
Task: Complete a practical implementation or investigation related to api fundamentals. Document the requirements, approach, evidence of operation, test results and any problems encountered.
Submission: Technical report, configuration evidence and supporting files where applicable.
Marking: Technical accuracy 40%, verification 25%, documentation 25%, safe practice 10%.
Assignment 5 — Week 10: Privacy and security
Task: Complete a practical implementation or investigation related to privacy and security. Document the requirements, approach, evidence of operation, test results and any problems encountered.
Submission: Technical report, configuration evidence and supporting files where applicable.
Marking: Technical accuracy 40%, verification 25%, documentation 25%, safe practice 10%.
Midterm examination — Week 6
Proposed format: 90 minutes; multiple-choice, short-answer and scenario questions based on Weeks 1–5.
Skills assessed: Technical terminology, configuration decisions, troubleshooting and safe practice.
Actual exam questions, answer keys and marking guidance will be prepared in the instructor-only Moodle question bank.
Final examination — Week 12
Proposed format: 120 minutes; cumulative knowledge questions, troubleshooting scenarios and technical interpretation covering the full course.
Exam delivery, identity verification, accessibility accommodations and academic integrity procedures must be finalized before student assessment begins.
Capstone project
Project brief: Deploy a local AI API, test response quality and document latency and resource use.
Deliverables: Design plan, implementation evidence, testing checklist, results, troubleshooting record and final technical report.
Rubric: Design 20%, implementation 35%, testing 25%, documentation 20%.
Proposed grading
- Weekly quizzes — 10%
- Five practical assignments and labs — 25%
- Midterm examination — 20%
- Final examination — 20%
- Capstone project — 25%
Student preparation
A computer capable of running virtual machines or accessing an approved remote lab is recommended. Some courses may require additional RAM, storage, networking equipment or licensed software. Course-specific minimum requirements and accessible alternatives will be published before delivery.
All security testing must be limited to systems owned by the student or explicitly authorized for testing.
Academic status
This page describes a proposed curriculum. Instructors, tuition, assessment dates, enrollment and any required regulatory approvals are not yet established. No academic credit or professional certification is promised.