BrowserOS works great with local models for Chat Mode. Run models completely offline — your data never leaves your machine.
Context Length
Ollama defaults to 4,096 tokens of context — this is too low for BrowserOS. Below 15K tokens, the context overflows and the agent gets stuck in a loop constantly trying to recover. Only Chat Mode will work at low context lengths. Set at least 15,000–20,000 tokens for local models to function properly.
Increasing context length uses more VRAM. Run ollama ps to check your current allocation. See the Ollama context length docs for more details.
Setup
The easiest way to run models locally.Start Ollama with higher context
Configure in BrowserOS
-
Go to
chrome://browseros/settings
-
Click USE on the Ollama card
-
Set Model ID to
qwen/qwen3-4b
-
Set Context Window to
20000
-
Click Save
Nice GUI if you don’t want to use the terminal.Load a model
Open LM Studio → Developer tab → load a model. It runs a server at http://localhost:1234/v1/.
Configure in BrowserOS
-
Go to
chrome://browseros/settings
-
Click USE on the OpenAI Compatible card
-
Set Base URL to
http://localhost:1234/v1/
-
Set Model ID to the model you loaded
-
Set Context Window to at least
20000
-
Click Save
Recommended Models
Pick a model based on your available RAM/VRAM. Smaller models are faster but less capable.
Lightweight (under 5 GB)
Good for machines with 8 GB RAM. Fast responses, suitable for simple chat tasks.
Mid-range (10–15 GB)
Needs 16+ GB RAM. Better reasoning, handles longer conversations well.
Heavy (60+ GB)
For workstations with 64+ GB RAM. Closest to cloud model quality.
Start with qwen/qwen3-4b if you’re unsure — it’s small, fast, and surprisingly capable for its size.
