AINewsnow

✨ The $0 Local coding agent is here ✨

35B parameter model. Running locally on a 12GB RTX 5070 laptop. 55 tokens/second. For comparison, that's roughly in range of what you'd get from Claude or ChatGPT over API. Powered by FreeToken, just published on GitHub. Qwen3.6-35b-A3B NVFP4 is what I'm using but they added support for Qwen3.8 too…

Read the full story at DEV Community — AI ↗

Timeline · 1 report

  1. 2026-11-11 09:19 · DEV Community — AI
    ✨ The $0 Local coding agent is here ✨

More stories

  1. Lifetime AI bundle offering access to Claude, Gemini and 20+ models discounted ahead of Black Friday — CNET AI
  2. I built a no-config way to host apps built in AI chats — DEV Community — AI
  3. Building a remote MCP server in ASP.NET Core: OAuth, client registration and the TLS bug we didn't expect — DEV Community — AI
  4. MCP Servers Explained: What They Are and Why Devs Should Care — DEV Community — AI
  5. Claude Website Builders Compared: Nine You Can Use From Chat (2026) — DEV Community — AI
  6. Does Booksy have an API in 2026? What a shop owner can actually connect to ChatGPT — DEV Community — AI
  7. Attach images from Claude or ChatGPT straight to your Refract posts — DEV Community — AI
  8. MCP Explained for Product Managers (2027 Guide) — DEV Community — AI

Get the daily brief of stories like this at 6:30 every morning →