Real AI agent use cases, with sources and setup prompts

Run a local model bigger than your laptop's memory

Janas streams mixture-of-experts weights from SSD so a 48 GB Qwen3-Next-80B model runs on a 32 GB laptop. The author measured 24-37 tokens per second writing versus 2.8 for llama.cpp on the same machine.

See pricing page1 hourAdvancedSource linked

Source

khalidkhair on Hacker News · 2026-10-12 · Project link

Written in our own words. Credit to the original author. Link checked 2026-10-17.

What they did

Janas streams mixture-of-experts weights from SSD so a 48 GB Qwen3-Next-80B model runs on a 32 GB laptop. The author measured 24-37 tokens per second writing versus 2.8 for llama.cpp on the same machine.

Result (as claimed)

Experimental, open source; 220 points on Hacker News.

Tools they used

Qwen

Cost: Pricing depends on the tools you pick; check each official pricing page.

Set it up

  1. Pick a contained repo or task

    Start on a branch or side project where mistakes are cheap.

  2. Install and configure

    Set up Qwen. Read what it can run on your machine and limit permissions where possible.

  3. Run it on a real task

    Give it a well-scoped issue and let it work. Review the diff like any pull request.

  4. Add guardrails

    Keep tests and CI in the loop, and never let an agent push to main or touch production secrets unattended.

Copy the full setup prompt

Paste into your agent and it will walk you through the setup, asking before anything that sends, posts or spends.

You are helping me set up this AI use case end to end in Claude Code.

Goal: Run a local model bigger than your laptop's memory
What the original author did: Janas streams mixture-of-experts weights from SSD so a 48 GB Qwen3-Next-80B model runs on a 32 GB laptop. The author measured 24-37 tokens per second writing versus 2.8 for llama.cpp on the same machine.
Reported result (as claimed by the author): Experimental, open source; 220 points on Hacker News.
Source: https://news.ycombinator.com/item?id=50063717
Tools they used: Qwen
Category: Dev & ops

Please:
1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like).
2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure.
3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data.
4. Finish with a checklist to run it again next time.

The Daily 5

Get five new use cases tomorrow morning

Free. Real sources. Unsubscribe any time.

Guides for this use case

How to add memory to coding agents · How to build agent memory and context layers · How to cut AI coding agent costs and token use

Related use cases

Dev & opsHacker News · Feyd

Run a 125B MoE coding-agent model on two 16 GB gaming GPUs

capy-flash runs Qwen3.8-Flash-Next (125B MoE) in NVFP4 on two RTX 5070 Ti cards. In the author's tests it finished 20 of 20 multi-step coding tasks with zero malformed tool calls and serves OpenAI- and Anthropic-compatible endpoints.

See pricing page1 dayAdvanced
Qwen