In this episode I sit down with Amir to get tactical about running local AI models as part of a daily workflow. We center on GLM 5.2 from ZAI, how it stacks up against frontier models like Opus 4.8, and how a fusion approach lets you sequence a heavy thinking model with a lighter execution model for the best output at the lowest cost. Amir walks through setup in Cursor and Codex via OpenRouter, shares real token-cost math, and demos GLM 5.2 refining a live app. By the end you will know how to start today, where local models shine, and how model chaining keeps spend in check.
Timestamps
00:00 – Intro
02:09 – GLM 5.2 and Z AI
04:01 – Specs: 1M context and Terminal Bench 2.1
05:22 – Making sense of benchmark scores
06:42 – Setup in Cursor or Codex with OpenRouter
10:18 – Local model upside: buy a machine, run tasks
11:42 – Token cost: 44 cents versus $2.38
13:36 – Future-proofing with an upfront hardware bet & The Uber subsidy analogy
16:49 – Model chaining and the vision workaround
19:23 – Token maxing vs routing tasks to the right model
20:54 – Answering the "cost is irrelevant" crowd
21:59 – Closing thoughts
Key Points
* GLM 5.2 ships with a 1M-token context window and scores 81 on Terminal Bench 2.1, landing about four points behind Opus 4.8.
* A fusion approach (a term OpenRouter coined) sequences models: plan with Opus, execute with GLM 5.2, review with Composer 2.5 or Codex 5.5.
* Running GLM 5.2 in the cloud through OpenRouter costs roughly 44 cents for a task that runs about $2.38 on Opus 4.8 — close to a 5X saving.
* You can start today with credit-based access: load $20 in OpenRouter and route tasks to the right model.
* For images, Amir uses Opus 4.8 to read screenshots and describe them, then hands the layout to GLM 5.2 to act on.
* Teams are shifting from token-maxing to output-maxing, making model governance and chaining the smart play
Numbered Section Summaries
1. The Promise: Local Models Catch Up — I open by framing the goal: a tactical look at how local models now keep pace with closed models, and how Amir puts them to work every day.
2. GLM 5.2 Arrives — Amir covers ZAI’s GLM 5.2 release: a 1M-token context window, an 81 on Terminal Bench 2.1, and strong long-horizon task performance, marking a clear leap from 5.1.
3. Reading Benchmarks by Vibes — We agree benchmarks feel abstract, so Amir favors building with the model and judging output directly. He sees about 62% where Opus reaches roughly 69%, then trusts hands-on testing to settle it.
4. Setup in Cursor and Codex — Amir lays out two paths: paste a ZAI API key into Cursor and override the OpenAI endpoint to add GLM 5.2 as a custom model, or use OpenRouter with a Codex profile and switch models from the CLI.
5. The Fusion Approach — Borrowing OpenRouter’s term, Amir describes sequencing models so each handles its strength: a thinking model plans, an execution model builds, and a reviewer polishes, keeping cost and performance balanced.
6. The Token Math — Amir maps a real example: 50k input and 85k output tokens land near Opus 4.8 quality for about 44 cents on GLM 5.2 versus $2.38 on Opus 4.8. I call out that 5X as a big deal at scale.
7. Future-Proofing and the Subsidy Clock — We compare today’s token subsidies to Uber’s early cheap rides. Amir suggests an upfront hardware investment now pays off as heavier future models arrive and subsidies wind down.
8. Governance, Chaining, and the Vision Workaround — Amir shares how teams overspend (think formatting an email with Opus 4.8 high thinking) and how chaining fixes it. For images, he routes screenshots through Opus 4.8, then hands the layout to GLM 5.2.
The #1 tool to find startup ideas/trends – https://www.ideabrowser.com/
LCA helps Fortune 500s and fast-growing startups build their future – from Warner Music to Fortnite to Dropbox. We turn ‘what if’ into reality with AI, apps, and next-gen products https://latecheckout.agency/
The Vibe Marketer – Resources for people into vibe marketing/marketing with AI: https://www.thevibemarketer.com/
FIND ME ON SOCIAL
X/Twitter: https://twitter.com/gregisenberg
Instagram: https://instagram.com/gregisenberg/
LinkedIn: https://www.linkedin.com/in/gisenberg/
FIND AMIR ON SOCIAL
Humblytics: https://humblytics.com/?via=community
X/Twitter: https://x.com/amirmxt
Youtube: https://www.youtube.com/@amirmxt
