@stevibe: I explored a further possibility with local models: Qwen3.6 35B A3B + NVIDIA LocateAnything-3B as a local Computer Use …
Summary
Demonstration of a local computer use agent combining Qwen3.6 35B A3B and NVIDIA LocateAnything-3B models to perform tasks like switching Mac display modes via screenshots, without requiring accessibility APIs, running entirely on local hardware.
View Cached Full Text
Cached at: 06/04/26, 04:00 AM
I explored a further possibility with local models: Qwen3.6 35B A3B + NVIDIA LocateAnything-3B as a local Computer Use agent (proof of concept).
In the demo, I asked it to switch my Mac to light mode. It did. Then back to dark. Did that too — finding the right toggle in System Settings, clicking it, and verifying the change itself.
It’s fully screenshot-based, so no Accessibility API needed. If it’s on screen, the agent can see it and act on it. This runs entirely on your own hardware — private, local, built from two small open models.
Similar Articles
@stevibe: Qwen3.6 35B A3B can't fill out a paper form on its own. But give it NVIDIA's LocateAnything-3B — the #1 trending model …
A demonstration shows that Qwen3.6 35B A3B combined with NVIDIA's LocateAnything-3B as a vision tool can accurately fill out a paper form by detecting field positions, proving that small models can collaborate to accomplish tasks beyond a single large model's capability.
@davis7: @0xSero helped me setup local models properly and I uh, had no idea these things had gotten this good Are they frontier…
The author highlights the impressive capabilities of the open-source Qwen 3.6-27B model running locally on an RTX 5090, noting its strong performance on programming tasks and comparing it favorably to commercial models, despite the complexity of local deployment.
Running Qwen3.6-35B-A3B Locally for Coding Agent: My Setup & Working Config
A detailed guide for running the 35B-parameter Qwen3.6 model locally on Apple Silicon with llama.cpp to power the pi coding agent, including optimized configuration flags and sampling parameters.
"Browser OS" implemented by Qwen 3.6 35B: The best result I ever got from a local model
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.
Localmaxxing (3 minute read)
The article analyzes the viability of running AI inference locally on a MacBook Pro, comparing a local Qwen 35B model against the cloud-based Claude Opus 4.5. It concludes that local models are 2x faster for routine tasks, making them a practical choice for half of daily workloads despite a slight capability gap.