deercanidae/ollama-precached-models repository overview

⁠Ollama cached models

This image contains the ollama tool packaged with two LLMs:

• Mistral⁠ for general chat (intruct variant)
• Stable-Code⁠ for use with llama-coder⁠ (stable-code:3b-code-q4_0 variant)

This combinaition is tailord to my use of the tool and fits my hardware specs. It has only been tested on a CUDA GPU.

If this project doesn't fit your needs, I'd encourage you to fork it and adapt it to yours.