Quest: Local Model Liberation
| Field | Value |
|---|---|
| Category | Challenge |
| Difficulty | Journeyman |
| Points | 100 |
| Deadline | 21 days |
| Evidence | Text + Link |
| Objectives | 5 |
Narrative Context
The cloud giants offer convenience, but true sovereignty requires the ability to run AI on your own terms. Local models mean your data stays yours, your costs become predictable, and you’re never cut off from your tools. This is the path to independence.
Transformation Goal
You will gain hands-on experience running LLMs locally, understand the trade-offs between local and cloud inference, and have a working setup you can build upon.
Objectives
Objective 1: Choose Your Weapon
| Field | Value | |——-|——-| | Points | 15 | | Evidence | Text | | Depends On | — |
Research local model options (Ollama, LM Studio, llama.cpp, etc.). Document your hardware specs and which tool you’ll use.
Objective 2: First Boot
| Field | Value | |——-|——-| | Points | 20 | | Evidence | Text + Link | | Depends On | Objective 1 |
Install your chosen tool and successfully run a small model (7B or under). Screenshot the output.
Objective 3: Push the Limits
| Field | Value | |——-|——-| | Points | 25 | | Evidence | Text | | Depends On | Objective 2 |
Run the largest model your hardware can handle. Document inference speed, memory usage, and quality observations.
Objective 4: Practical Application
| Field | Value | |——-|——-| | Points | 25 | | Evidence | Text | | Depends On | Objective 3 |
Use your local model for a real task (summarization, coding help, writing). Compare results to a cloud model.
Objective 5: Share the Knowledge
| Field | Value | |——-|——-| | Points | 15 | | Evidence | Link | | Depends On | Objective 4 |
Post your setup guide and findings to the WhatsApp group or write a short blog post.
Resources
Design Notes
This quest directly supports the guild’s sovereign AI pillar. The final objective ensures knowledge sharing, turning individual learning into community asset.