"Browser OS" implemented by Qwen 3.6 35B: The best result I ever got from a local model
Summary
A user reports achieving impressive results with Qwen 3.6 35B running a 'Browser OS' implementation locally, highlighting the model's capability for complex task execution without cloud dependencies.
Similar Articles
Qwen 3.8 27b is a amazing model, for the first time I see a local model found its own away to open a browser and test
A user describes an unexpected behavior where the quantized Qwen 3.8 27B model opened a browser to test code autonomously during development, highlighting emergent capabilities.
@ngxson: Qwen3.6-27B running 100% on WebGPU. Not the best speed but still
A developer demonstrates running the Qwen3.6-27B AI model entirely on WebGPU in a browser, though speed is not optimal.
Qwen3.8-27b has the highest level of "agency" I've ever seen in a local model
The article praises Qwen3.8-27b for its remarkable agency in executing complex, multi-step tasks with numerous tool calls without human intervention, all running locally on consumer hardware like an RTX 3090.
Qwen3.6 35B-A3B on a Laptop: My Zero to One Moment
The author shares their experience running Qwen3.6 35B-A3B locally on an ASUS Zenbook Pro 14, achieving 27 TPS at 32k context, marking a personal milestone towards fully local AI for privacy.
New qwen3.8:27b on a 39k line C to single-file HTML / three.js port
An experiment comparing the qwen3.8:27b model with Claude Opus 5 on a complex code porting task from C to HTML/three.js, highlighting that local models struggle with long contexts and require effective prompting to avoid poor results.