2 comments

  • denn-gubsky 6 hours ago

    Try qwen3-coder or qwen3-coder-next models which fit into your configuration. This is team-of-experts model which may load only actual experts into GPU.

    • limondas 4 hours ago

      Thanks for your reply. But it's to big for my PC. In PC around 1.5GB models got 20 token/s , which is too low for agentic workflow.