Browser-Based Local LLM Chat
Experience local LLM conversations running entirely in your browser.
Complete privacy with no data sent to external servers.
LFM2.5-2.6B (Transformers.js)
System Prompt
Temperature
0.7
Top P
0.9
Max Tokens
2,048
Tool Calling
Storage Management
Downloaded models consume local disk space.
Used Space: 0 B
Start a Conversation
Chat with AI running entirely in your browser. Your conversations are private and never leave your device.
Try one of these prompts:
Powered by Transformers.js — High-performance in-browser LLM inference using WebGPU
About Browser-Based LLM Chat
How to Use
- Select a Model: Choose from available models like Qwen3.5, Qwen3, or Mistral based on your needs and hardware.
- Wait for Download: On first use, the model will download and cache in your browser for future sessions.
- Start Chatting: Type your message and press Enter. Responses stream in real-time.
- Customize Settings: Adjust temperature, system prompt, and other parameters in the Settings panel.
Browser Support
WebGPU is required for GPU-accelerated inference. Chrome and Edge have the best support. A dedicated GPU with 2-8GB VRAM is recommended for optimal performance.
Security & Privacy
100% Private: All processing happens locally in your browser. No data is sent to any server.
Your conversations, prompts, and responses never leave your device. Chat history is stored only in your browser's local storage and can be cleared anytime.
Frequently Asked Questions
On first use, the selected model downloads and is cached in your browser. Download size and load time vary by model. Larger models need more VRAM and take longer to load; cached models usually load faster on later visits.
WebGPU is a new web standard that may not be enabled by default in all browsers. In Chrome/Edge, go to chrome://flags and enable "WebGPU". In Firefox, set "dom.webgpu.enabled" to true in about:config. Also ensure your GPU drivers are up to date.
LFM2.5-2.6B is the recommended default for Transformers.js (and Qwen3.5-2B for WebLLM). Other choices include Qwen3-8B, Mistral-7B, Qwen3-0.6B, and GPT-OSS-20B. Larger models generally need more memory, while Qwen3-0.6B is the low-resource option.
No. All processing is done entirely in your browser using WebGPU. Your conversations are stored only in your browser's localStorage and never sent to any server. You can export or clear your chat history at any time.
You might also like
Explore more interactive tools and demos.
