LM

Luis Mori Guerra

Engineering Manager / Technical Lead

HomeAbout MeTopics

Recent Articles

Do We Need Deep Thinking? Why Fable 5.1 and Astra Look Smart and Gemini 3.8 Flash Looks DumbOn-Device AI on Phones: The 4 tok/s RealityBrowser LLMs + WebMCP + MCP UI: The Coming Frontend StackYour AI Assistant Might Be Cheating on Its HomeworkWhat Is an AI-Native App? A Working Definition, Architecture, and Practical Test

Topics

AI Agents81AI32Architecture28LLM25Claude Code22AI Engineering21Cursor21Loop Engineering20
luismori.
ArticlesAboutTopicsGitHubConnect
← All topics

WebLLM

A topic hub collecting every article tagged WebLLM. Use it to explore related posts and follow this theme across the site.

1 article

Explore More Topics

AI Agents AI Architecture LLM Claude Code AI Engineering
AI Agents Browser AI WebGPU WebLLM Mobile Benchmarks Frontend Chrome

On-Device AI on Phones: The 4 tok/s Reality

Phones can run LLMs in the browser — at 4–9 tok/s on flagships, with tab crashes, 76-second first tokens, and feature detection that lies. A mobile benchmark study with a warmup-gating pattern you can ship.

Sep 17, 2026 23 min read

Quick find

Search the blog

Search by topic, title, framework, or pattern.

Loading search…