Skip to main content
Back to Academy catalog
BuilderIntermediate

Open-Source LLMs for Enterprise

A 65-minute decision guide — Llama, Mistral, Phi, Qwen; Ollama, vLLM, and Azure ML; fine-tuning, cost, and sovereign deployment patterns.

65 min·8 chapters·Technical practitioner · Director·Free

Last updated: 2026-05-19

What you'll learn

By the end of this course you'll be able to:

  • Why open-source — and the honest cases where a hosted API still wins
  • Model selection across Llama, Mistral, Phi, and Qwen families
  • Self-hosting paths: Ollama, vLLM, TGI, Azure ML private endpoints
  • Fine-tuning approaches — LoRA, QLoRA, full fine-tunes, and when each fits
  • Cost and performance tradeoffs at realistic enterprise concurrency
  • Air-gapped and sovereign deployment patterns for regulated environments

Who this is for

Senior engineers, ML platform leads, and tech directors evaluating or operating open-source LLMs at enterprise scale. Especially relevant for teams with sovereignty, residency, or per-token cost pressure — and for regulated sectors (BFSI, healthcare, government) where data simply cannot leave a controlled boundary.

Curriculum

8 chapters · 2 hands-on exercises · capstone challenge

Each chapter ends with the learning objectives ticked off. Quizzes are auto-graded with feedback; exercises are open-ended and produce artifacts you can take to your team.

1

1. Why open-source — and when not

8 min
  • Frame the open-source decision around sovereignty, cost curve, and roadmap risk
  • Recognize the 3 cases where a hosted API is still the right answer
2

2. Model selection — Llama, Mistral, Phi, Qwen

9 minQUIZ
  • Compare model families on capability, licensing, and multilingual coverage
  • Match model size to task — and resist the “bigger is better” default
3

3. Self-hosting — Ollama, vLLM, TGI, Azure ML

9 minEXERCISE
  • Pick the right serving stack for your latency, throughput, and ops profile
  • Configure vLLM and TGI for production concurrency, not laptop demos
4

4. Fine-tuning approaches

9 minQUIZ
  • Choose between LoRA, QLoRA, and full fine-tuning based on data and goal
  • Avoid fine-tuning for problems that retrieval or prompting would solve cheaper
5

5. Cost and performance tradeoffs

8 min
  • Model the total cost of ownership — GPU hours, ops, evals, and incident load
  • Compare per-token economics against hosted APIs at your real concurrency
6

6. Air-gapped and sovereign deployment

8 minEXERCISE
  • Architect deployments that satisfy data-residency and air-gap requirements
  • Apply the patterns that actually pass regulator and CISO review
7

7. Operational considerations

7 minQUIZ
  • Plan for model upgrades, security patches, and quantization rollouts
  • Design observability across GPU, model, and request layers

Capstone: Capstone: Your open-source LLM decision pack

7 min
  • Document the model, serving, and fine-tuning decision for a real workload
  • Produce the TCO and sovereignty case your steering committee will accept

Capstone deliverable: Every learner who completes this course produces «Your Open-Source LLM Decision Pack» — a tangible artifact you take back to your organization.

Curriculum live · full chapter content rolling out through 2026.

The outline, learning objectives, references, and capstone deliverable are published. Full chapter content (video, narration, exercises) ships progressively. Get notified when each chapter goes live.

Get notified when chapters ship

References & sources

Built on cited sources — not vibes.

Every course is researched fresh against vendor documentation, regulatory sources, and peer-reviewed work. Sources used in this course:

Meta Llama — Models and Licensing

Meta · Source link

Mistral AI Documentation

Mistral AI · Source link

vLLM Documentation

vLLM Project · Source link

Ollama — Local Model Runtime

Ollama · Source link

Hugging Face Documentation

Hugging Face · Source link

Course details

Track

Builder

Level

Intermediate

Audience

Technical practitioner, Director

Function

IT & Engineering

Industry

Cross-Industry

Stack

Open-source

Paired Gennoor Way phase

innovate, build

Format

video, hands-on, interactive