Kilo is the VS Code extension that actually works with every local LLM I throw at it

Kilo lets you switch between local and cloud models in a snap.

XDA
@XDAOfficial @xda-developers-XDAOfficial I use that and can confirm. This coding agent works really well with Ollama BUT you need LOTS of context window size, which translates into TONS of KV cache and VRAM required. RTX3090 with 24GB can handle at best 32k context in 24-30B models