Sign up to save your podcasts
Or
Share Ep 679: A 284B Model Ran on a MacBook Last Week — Jun 22
Share to email
Share to Facebook
Share to X
Share to email
Share to Facebook
Share to X
Or
Ep 679: A 284B Model Ran on a MacBook Last Week — Jun 22
DeepSeek V4 Flash's 284 billion parameters now fit on a consumer laptop via Dwarf Star's architecture-aware quantization. GLM 5.2 pushes mixture-of-experts to 744B with million-token context at manageable cost. Local AI is no longer theoretical.
Source episodes:
- 5 Things I Wish I Knew Before I Started AI Coding (Robin) https://www.youtube.com/watch?v=iTB5moCuQPY
- This 284B Model Shouldn't Fit On Your Laptop. It Does (Engineer Prompt) https://www.youtube.com/watch?v=9gHcmhUDJfw
- Why Local AI Matters and How to Use It (The AI Daily Brief) https://anchor.fm/s/f7cac464/podcast/play/121785944/https%3A%2F%2Fd3ctxlq1ktw2nl.cloudfront.net%2Fstaging%2F2026-5-21%2F426551944-44100-2-eace034712683.mp3
- GLM 5.2: What Makes it So Special? (Engineer Prompt) https://www.youtube.com/watch?v=DukEhXcrDz4
View all episodes
By Paul BrownDeepSeek V4 Flash's 284 billion parameters now fit on a consumer laptop via Dwarf Star's architecture-aware quantization. GLM 5.2 pushes mixture-of-experts to 744B with million-token context at manageable cost. Local AI is no longer theoretical.
Source episodes:
- 5 Things I Wish I Knew Before I Started AI Coding (Robin) https://www.youtube.com/watch?v=iTB5moCuQPY
- This 284B Model Shouldn't Fit On Your Laptop. It Does (Engineer Prompt) https://www.youtube.com/watch?v=9gHcmhUDJfw
- Why Local AI Matters and How to Use It (The AI Daily Brief) https://anchor.fm/s/f7cac464/podcast/play/121785944/https%3A%2F%2Fd3ctxlq1ktw2nl.cloudfront.net%2Fstaging%2F2026-5-21%2F426551944-44100-2-eace034712683.mp3
- GLM 5.2: What Makes it So Special? (Engineer Prompt) https://www.youtube.com/watch?v=DukEhXcrDz4