CHands-on reviewedEditor's pick
Coursera
Generative AI with Large Language Models
For: Engineers who plan to fine-tune or self-host LLMs
4.8(4.2K)
Intermediate · ~16 hours (3 weeks at 5h/wk) · Free to audit · $49 cert
Generative AI with Large Language ModelsvsPractical Deep Learning for Coders (fast.ai)
Side-by-side comparison on level, duration, pricing, instructor, tier. Editor verdict on which course wins for which buyer.
C
Coursera
Generative AI with Large Language Models
The most comprehensive LLM-internals course in the under-20-hour bucket. Covers transformer architecture, pretraining, fine-tuning (instruction + PEFT/LoRA), RLHF, and deployment-side concerns (cost, throughput, scaling). Built on AWS Bedrock for labs, but the architectural content transfers to any platform. Skip if you already know how transformers work — most of the value is in the middle weeks on fine-tuning and RLHF, which is harder to find elsewhere.
fast.ai
fast.ai
Practical Deep Learning for Coders (fast.ai)
The defining contrarian course in ML education. fast.ai's top-down philosophy — train a working image classifier in lesson 1, understand the math by lesson 6 — works for some learners and frustrates others. We recommend it for engineers who learn by doing rather than by first principles. The course extends to LLMs in later lessons (Jeremy regularly updates), and the companion book ('Deep Learning for Coders with fastai and PyTorch') is genuinely the best paper book on practical deep learning. Free; the only cost is the 70-hour commitment. If Karpathy's Zero-to-Hero is too math-heavy, this is the alternative.
Side-by-side
| Dimension | Generative AI with Large Language Models | Practical Deep Learning for Coders (fast.ai) |
|---|---|---|
| Provider | Coursera | fast.ai |
| Editorial tier | Hands-on reviewed | Curated |
| Level | Intermediate | Intermediate |
| Format | self paced | self paced |
| Duration | ~16 hours (3 weeks at 5h/wk) | ~70 hours (8 lessons + projects) |
| Pricing | Free to audit · $49 cert | Free |
| Instructor | Antje Barth, Mike Chambers, Shelbee Eigenbrode, Chris Fregly — AWS Generative AI Specialists | Jeremy Howard & Sylvain Gugger — Founder fast.ai; Hugging Face research engineer |
| Rating | ★ 4.8 (4,231 on Coursera) | No public rating |
| Topics | llm fundamentals, fine tuning | llm fundamentals, fine tuning, computer vision |
| Last verified | 2026-05-23 | 2026-05-23 |
Pros & cons
Generative AI with Large Language Models
Pros
- +Best treatment of fine-tuning + RLHF in any short-form course
- +Auditable for free — you only pay for the Coursera Plus certificate
- +Hands-on AWS Bedrock labs (transferable patterns)
Cons
- −AWS-specific labs — if you don't have an AWS account, the lab portion is awkward
- −16-hour commitment is a real ask for non-engineers
Practical Deep Learning for Coders (fast.ai)
Pros
- +Top-down pedagogy — you ship working models from lesson 1
- +Free, regularly updated, by one of the most respected practitioners in the field
- +Excellent companion book if you prefer paper
Cons
- −70 hours is a real ask
- −Pedagogy is contrarian — some learners want first principles, not top-down
- −Less LLM-focused than the field demands in 2026; deep-learning generalist
Which course is for whom?
Generative AI with Large Language Models
Best for
- · Engineers who plan to fine-tune or self-host LLMs
- · Anyone evaluating "should we fine-tune or just use a bigger model?"
Not ideal for
- · Beginners — assumes ML basics (gradient descent, embeddings)
- · People who only want to use LLM APIs, not understand them
Practical Deep Learning for Coders (fast.ai)
Best for
- · Engineers who learn by doing, not by deriving
- · People who tried Karpathy's course and bounced off the math density
Not ideal for
- · Anyone needing LLM-specific depth — this is broader deep learning
- · Time-constrained learners — there are shorter paths
Editor's short verdict
Take Generative AI with Large Language Models first — it's our Tier-1 pick on this topic and the editorial confidence is higher. Practical Deep Learning for Coders (fast.ai) is a reasonable alternative if you've already taken or evaluated the Tier-1 option.
fast.aiCurated
fast.ai
Practical Deep Learning for Coders (fast.ai)
For: Engineers who learn by doing, not by deriving
Intermediate · ~70 hours (8 lessons + projects) · Free
Other comparisons
Similar courses you might also be considering.
- Compare Generative AI with Large Language Models vs Machine Learning Specialization (Andrew Ng) →
- Compare Generative AI with Large Language Models vs AWS Generative AI Learning Plan →
- Compare Generative AI with Large Language Models vs Hugging Face LLM Course →
- Compare Practical Deep Learning for Coders (fast.ai) vs AWS Generative AI Learning Plan →
- Compare Practical Deep Learning for Coders (fast.ai) vs Hugging Face LLM Course →
- Compare Practical Deep Learning for Coders (fast.ai) vs Google Cloud Generative AI Learning Path →