← All 186 courses
AI-208 AI & Data

Model Compression: Quantization, PEFT, QLoRA & Distillation

Make big models economically deployable: quantization formats and their quality cost, parameter-efficient fine-tuning with LoRA/QLoRA, and distillation of large-model behaviour into small servable models — anchored in a cost-per-request business case, not just benchmarks.

B5Advanced
5modules
31skill atoms
1role journey
Curriculum

What this course covers.

5 modules, 31 named skill atoms. Expand any module to see them.

1Why Compression Pays7 skill atoms
memory mathlatencyunit economicsbytes-per-weight mathVRAM ceilingsbatch throughput gainsGPU-hour cost
2Quantization in Practice7 skill atoms
INT8/4-bitcalibrationquality deltasGPTQ & AWQbitsandbytes NF4per-channel vs per-tensor scalesperplexity regression checks
3LoRA & QLoRA6 skill atoms
adapter theoryGPU-frugal fine-tuning labrank & alpha selectiontarget module choiceadapter mergingmulti-adapter serving
4Distillation6 skill atoms
teacher-student setupcapability transfersoft-label losstemperature scalingsynthetic data generationcapability loss audit
5₹-per-Request Verdict5 skill atoms
fine-tuned small model vs hosted API reportamortized GPU costutilization assumptionsbreak-even volumequality gap accounting
Where it fits

AI-208 in a role journey.

This course appears in 1 of our 45 role journeys. Here is what a learner takes immediately before and after it in each.

GenAI / LLM Engineer

Capstone stage
AI-216AI-208AI-312

Roles this course serves

The capability ladder

This course is authored to band B5.

Every course we run is written to one rung of the CASI ladder, so a plan can be assembled to take a team from where they are to where they need to be.

What do B1–B6 mean?The CASI Capability Ladder — click to expand

Every course targets a band on the CASI Capability Ladder — our six-band proficiency scale, anchored to open standards (O*NET, ESCO, NICE, NIST AI RMF, Bloom's). A band tells you how deep a course goes, and what evidence proves it.

What the learner can doTypical evidence
B1
AwareUnderstands concepts and vocabulary; uses tools with guidance
Knowledge checks
B2
FoundationPerforms standard tasks correctly in familiar contexts
Guided labs, autograded exercises
B3
PractitionerDelivers complete pieces of work independently
Scenario labs, proctored hands-on exams
B4
ProfessionalHandles production-grade complexity, trade-offs and failure modes
Break-fix drills, design defenses
B5
AdvancedEngineers systems end-to-end under constraints; leads others
Rubric-scored capstones, vivas
B6
ExpertSets direction; recognised authority across teams
Portfolio + panel evaluation

A note on B6. Courses in this catalog target B1–B5. B6 is not taught — it is recognised, through a portfolio and a panel, once someone is setting direction for others. Every journey here is built to land a learner at B5.

Next step

Run AI-208 for your team.

This course runs at several lengths depending on how deep you need to go and how much of it your people already have. Tell us who is being trained and we will scope it.

Add it to a training plan Talk to our team Check your team’s level free