🤖 Local AI Chat (CPU)
Model:
Qwen 3.5 0.8B Q8_0 (~810MB)
Qwen 3.5 0.8B Q5_K_M (~650MB)
Qwen3 0.6B Q4_K_M (~530MB)
Qwen3 1.7B Q4_K_M (~1.2GB)
Load
👋 Select a model and click Load. First load downloads the model, then it's cached in browser.
Send
Not loaded