Running Local LLMs in VS Code | Merge Conflict ep. 514
In this episode James and Frank dive into running AI coding models locally versus in the cloud—BYOK/Open Router, VS Code’s chat/agent harness, model runners (Olama, vLLM), and the practicality of 27B models on a 3090 using 4‑bit quantization. They share hands-on takeaways—how recent engineering (MT/MTPLX) boosts inference to usable token rates, when auto model selection makes sense, cost and hardware trade‑offs, and why local models can liberate your workflow while still needing smarter, unified tooling. Hosts: @praeclarum and @JamesMontemagno 00:00:00 - Intro & Guatemala Banter 00:04:00 - AI News & BYOK Intro 00:09:00 - Open Router & VS Code Models 00:16:00 - Running Local Models Setup 00:24:00 - Model Quality & Quantization 00:31:00 - Cloud vs Local Workflows 00:37:00 - Performance & Inference Speedups 00:44:00 - Hardware Limits, Future, Closing Merge Conflict: https://www.mergeconflict.fm Subscribe: https://www.mergeconflict.fm/subscribe Patreon: / mergeconflictfm #dotnet #podcast #mergeconflict

UI.md - Opinionated design rules for coding agents | Merge Conflict ep. 523

Evolving Agent Session Management | Merge Conflict ep. 516

AI Has A Hidden Debt Problem

Polish Matters: UI, Icons, and AI Design Fails | Merge Conflict ep. 521

Shipping More, Understanding Less

CHOSEN ONE!! YOUR IDENTITY REVEAL JUST SHOOK THE INTERNET... AND THEIR MINDS

Mini-LED, IPS, and the Great Monitor Rabbit Hole | Merge Conflict ep. 515

Inside the New GitHub Copilot App: Sessions, Canvases, Automations | Merge Conflict ep. 520

No Boss, No Money: The Raw Reality of China’s Gen-Z Freelancers

Keynote: After the AI Hype – What’s Real, and What’s Next - Richard Campbell - 2026

1 Button Press Can Hack Millions of Cars

Windows is Back! New Microsoft AI Coding Models | Merge Conflict ep. 518

The REAL reason the US can’t beat Iran

China Is About To Pop The AI Bubble

How AI agents & Claude skills work (Clearly Explained)

8GB of RAM Isn't Good Enough #MacBookNeo | Merge Conflict ep. 505

Plan First, Think Less: Save Tokens, Improve Code| Merge Conflict ep 517

Don't Hang Up On AI Scammers. Do THIS Instead.

iCircuit UI Roast: Toolbar, Popovers, and Polish | Merge Conflict ep. 507

