# Show HN: Maple – Run Gemma 4 26B on a 6GB Laptop GPU at 45 TPS \(Sub\-2\-BPW\)

- HackerByte page: <https://hackerbyte.net/en/stories/a-technique-enabling-efficient-execution-of-advanced-ai-models-gemma-4-26b-on-lo-50415106>
- Original source: <https://amsach.github.io/maple/>
- Hacker News discussion: <https://news.ycombinator.com/item?id=50415106>
- Submitted to Hacker News: 2026-11-08T17:13:03.000Z

A technique enabling efficient execution of advanced AI models \(Gemma 4 26B\) on low\-VRAM laptop GPUs at high throughput.

## AI-generated summary

No summary is available in this language yet.