Codex + Ollama = Free Unlimited Coding AI

You are helping me turn one specific YouTube video into real, durable learning.

Source video:
- Title: Codex + Ollama = Free Unlimited Coding AI
- URL: https://www.youtube.com/watch?v=qo40REk9wNU
- Topic: Codex + Claude Workflows
- My current learning frame: Install Ollama 0.24+, pull gemma4:e4b, run 'ollama launch codex app' to open Codex on the local model, prompt it to build a landing page, and render its HTML to evaluate whether a free 4B local model is good enough for your workflow.
- Why this matters: New playlist item from WorldofAI; queued for transcript-backed review, topic mapping, and a practical learning artifact.

Transcript anchors from this exact video:
- 0:17 / Evidence 1: "inside codex and use its AI coding education abilities completely for free. This is a huge moment for local AI workflows. For those who do not know, codex is open AI's AI coding agent that helps you build,..."
- 2:44 / Evidence 2: "want to know what model will work locally with your own compute. This is only if you're going to be installing a model locally. Obviously, you have the ability to use their API so that you can use..."
- 5:07 / Evidence 3: "finishes installing, we can then directly use it with Codex. Also, just make sure you have the latest update of Ollama, that is 0.24 and above, otherwise this won't work. So, it looks like it has finished installing..."
- 7:34 / Evidence 4: "parameter model locally outputting code like this. This is where you can basically leverage this beautiful harness to accomplish any task. You can use skills, you can use all of the capabilities of Codex now with Ollama with..."

Video-aware target:
- Prompt lane: Local model/runtime
- Mechanism to extract: Identify why the local setup works or fails for this specific agent task, not whether local models are generally good.
- Artifact to produce: A local model/runtime fit sheet with hardware constraints, model choice, endpoint setup, task benchmark, and fallback rule.
- Artifact must include: hardware; runtime; model/quantization; endpoint; agent integration; benchmark/fallback

Your task:
1. Use the transcript anchors above as the primary source packet. If you add outside context, label it clearly as outside context and keep it secondary.
2. Create a source-check table with columns: timestamp, claim, transcript support, what the demo proves, confidence, and what still needs verification.
3. Extract the actual teachable mechanism from the video: Identify why the local setup works or fails for this specific agent task, not whether local models are generally good. Do not invent claims that are not supported by the title, lesson frame, or transcript anchors.
4. Build a reusable learning artifact: A local model/runtime fit sheet with hardware constraints, model choice, endpoint setup, task benchmark, and fallback rule.
5. Include:
   - a plain-English definition of the core idea
   - a diagram or structured model using this sequence: Task -> Hardware -> Model/quantization -> Runtime endpoint -> Agent tool loop -> Benchmark task -> Fallback
   - answers to these source questions: What machine/runtime is shown? | What task exposes the model limit? | What setup change improves the loop?
   - 3 concrete examples that apply the video idea to real agentic work, such as Ollama or LM Studio coding endpoint; MLX Apple Silicon runner; DGX-backed Hermes session
   - 2 failure modes the video helps prevent, chosen from the transcript evidence and these likely risks: using a local model like ChatGPT; ignoring latency/context limits; no benchmark task
   - a checklist for the next real workflow, focused on: task fit, runtime setup, latency/context, tool loop, fallback
   - one practical exercise with a clear done signal: Choose one real coding task and specify the pass/fail benchmark for a local model.
6. Add a "learning transfer" section: what changes in my workflow tomorrow if I actually learned this?
7. Add a "source check" section that cites which transcript anchor supports each major takeaway.

Quality bar:
- Make this specific to "Codex + Ollama = Free Unlimited Coding AI", not a generic Codex + Claude Workflows essay.
- Tie each harness element to a transcript anchor that names a tool, state boundary, permission, model behavior, or verification step.
- Prefer operational examples, failure modes, and reusable artifacts over broad definitions.
- Call out uncertainty instead of smoothing over weak evidence.
- Avoid these generic drifts: local-model ideology; hardware specs without workflow fit; benchmarks unrelated to the actual task.
- If evidence is weak or missing, stop and say what transcript segment or timestamp needs review instead of guessing.
- Finish with a concise artifact I could paste into my learning app.