Running LLMs in the Browser with Three.js

kept by eddie sep 04

Three-LLM enables running GPT-2, SmolLM2, Qwen, and Phi language models in the browser by converting their inference graphs into Three.js TSL compute shaders on WebGPU.

Alibaba's small, open source Qwen3.5-9B beats OpenAI's gpt-oss-120B and can run on standard laptops
Alibaba's Qwen3.5-9B outperforms OpenAI's 120B-parameter gpt-oss on benchmarks while being 13 times smaller and capable of running on standard laptops.
also on Qwen3.5, Hugging Face, #open-source, #developer-tools
We're starting to leave the territory where you'd test an LLM by e.g. "create an svg of pelican on a bicycle". As one idea to generalize it,
Opus 5 used a 1M-token budget to generate 5,500 lines of three.js code that procedurally renders the opening of Lord of the Rings.
also on Three.js, #web-development, #ai-coding, #developer-tools
Bruno Simon – 3D Portfolio
Bruno Simon's interactive 3D portfolio lets visitors drive a car through a whimsical world, showcasing his Three.js skills while sparking debate on practicality versus creativity.
also on Three.js, #developer-tools
Give Your Coding Agents a Memory You Own
funes provides a local, searchable memory layer for coding agents like Claude Code and Codex, letting them retrieve past decisions without rebuilding context.
also on Hugging Face, #open-source, #ai-coding, #developer-tools
9 theses on AI | Sarthak Munshi
AI progress is constrained by long-task reliability, labor reallocation, cost inefficiencies of general APIs, the declining value of raw coding skills, inadequate benchmark testing, the limits of formal verification without strong specs, memory-bound local hardware advantages, the shift from data to environment-driven training, and the rising competitiveness of US open-weight models.
also on Hugging Face, #open-source, #ai-coding, #developer-tools