I've made another custom LLM. This one is a 7GB version of Qwen 3.8 27B that can be fully run on an 8GB GPU. I call it N...

I've made another custom LLM. This one is a 7GB version of Qwen 3.8 27B that can be fully run on an 8GB GPU. I call it NanoFlare.Local AI takes the power away from the big providers and consumes far less resources. If you have to use AI, running open weights on your own PC is a much better option. And I hope either NanoFlare or MicroFlare can help you do that.https://microflare.bearblog.dev/nanoflare-compresses-qwen-27b-down-to-fit-on-an-8gb-gpu/#localAI #localLLM #selfhosted #ai #llm #qwen #openweights #openmodels