vexp-ai/vexp-devmind-v1-GGUF

vexp-devmind v1 (GGUF, Q4_K_M)

Local LLM used by the vexp code-intelligence pipeline. Runs entirely on the user's machine.

Available as:

• npm: vexp-cli
• VS Code: Vexp extension

Quantization	Q4_K_M (llama.cpp / GGUF)
File	vexp-devmind-v1-Q4_K_M.gguf
Min RAM	4 GB
License	MIT

Intended use

This model is consumed exclusively by the vexp runtime. It is not a general-purpose chat model and produces terse, structured outputs that require the vexp runtime to be useful.

Install via either entry point:

CLI (npm):

npm install -g vexp-cli
vexp setup-llm --install

VS Code extension: Install Vexp from the marketplace, then click "Install LLM" in the vexp sidebar (or accept the first-run prompt).

Out-of-scope

Conversational chat, long-form generation, general reasoning. Use a general-purpose model for those tasks.

License

MIT.