Skip to main content
PromptQuorumPromptQuorum
Home/Power Local LLM/WeChat Bot with Local LLM: Personal Assistant 2026
Productivity & Knowledge Tools

WeChat Bot with Local LLM: Personal Assistant 2026

··By Hans Kuepper · Founder of PromptQuorum, multi-model AI dispatch tool · PromptQuorum
Read in:
🇺🇸en🇩🇪de🇫🇷fr🇯🇵ja🇨🇳zh🇪🇸es🇧🇷pt🇸🇦ar🇰🇷ko

You can build a WeChat personal assistant bot using WeChatFerry + Ollama in 2026. The bot runs entirely on your Windows PC, uses a local LLM (Qwen3 8B or 14B), and responds in real-time to WeChat messages without sending data to any cloud API.

This page contains links to third-party products for reference. PromptQuorum is not enrolled in any affiliate program — these are plain links that earn no commission. Clicking links and your next steps are entirely your own responsibility. These links do not represent any endorsement or verification by PromptQuorum.

Key Takeaways

  • WeChatFerry + Ollama: the recommended local WeChat bot stack for 2026
  • Qwen3 8B: best local model for Chinese-language WeChat responses
  • Windows required: WeChatFerry hooks into the WeChat PC client (Windows only)
  • Setup time: 30–60 minutes for someone comfortable with Python
  • No cloud API: all inference runs locally, no message data sent externally
  • Risk: WeChat ToS prohibits automated bots — use for personal assistants only
  1. 1
    Install Ollama and pull Qwen3 8B
    Why it matters: Download Ollama from ollama.com and run: `ollama pull qwen3:8b`
  2. 2
    Log in to WeChat PC
    Why it matters: Open WeChat on Windows and scan the QR code to log in. Keep it logged in and running in the background.
  3. 3
    Install WeChatFerry
    Why it matters: Install via pip: `pip install wcferry`. WeChatFerry injects into the WeChat process to expose a message API.
  4. 4
    Create the Python message handler
    Why it matters: Create `wechat_bot.py` with WeChatFerry client, Ollama HTTP API calls, and message routing logic.
  5. 5
    Test with a self-message
    Why it matters: Send a WeChat message to yourself starting with "@ai" and verify the bot responds within 10 seconds.
  6. 6
    Add conversation history
    Why it matters: Store the last 10 messages per contact in a dict to enable multi-turn conversation context.
  7. 7
    Run as a background service
    Why it matters: Use NSSM (Non-Sucking Service Manager) to run the Python script as a Windows service that starts automatically.
ModelSizeChinese QualitySpeed (CPU)Speed (8GB VRAM)
Qwen3:8b4.7 GBExcellent3–5 tok/s30–45 tok/s
Qwen3:14b9 GBBest1–2 tok/s15–20 tok/s
Qwen3:3b2 GBGood8–12 tok/s60+ tok/s
Llama3.1:8b4.7 GBModerate3–5 tok/s30–45 tok/s

Does this WeChat bot work on Mac?

No. WeChatFerry requires Windows and hooks into the WeChat Windows PC client via DLL injection. macOS users can run Windows in a virtual machine (Parallels or VMware Fusion) to use this setup.

Will my WeChat account get banned for using a bot?

WeChat prohibits automated bots in its Terms of Service. Accounts detected using automation tools risk temporary suspension or permanent ban. Use only for personal productivity at low message volumes.

What is the best Ollama model for Chinese WeChat messages?

Qwen3 8B is the best balance of quality and speed for Chinese-language WeChat responses — excellent Chinese comprehension, fast enough on most hardware, and the 4.7GB model fits in 8GB VRAM.

Can the bot handle group chats?

Yes. WeChatFerry exposes group messages with the room ID. Modify the on_message handler to check msg.roomid and filter which groups the bot should respond in. Add a trigger keyword to avoid responding to every group message.

← Back to Power Local LLM