GPU is not being fully utilized and ollama/qwen2.5:32b is slow

[bolto90]

This is due to the increased context size, I’ve just put a PR in to allow customising this through the env file with some recommended sizes for VRAM

New Qwen 2.5 Coder 32b Absolutely CRUSHING it!

I’ve just put a pull request in to allow easy changing of the context size which help reduce the vram requirements