Trying to run Llama model that is downloaded on my server locally using huggingface hub

[iamsp]

Hi @zinyando I am unable to use llm using LM Studio. Could you please guide if you have any idea?
I’ve posted my query here:

Unable to use HuggingFace, OpenRouter nor Local LLM using LMStudio. Please help

I’ve been working on a small project which needs multiple LLM calls. I’ve been using Together API but credit runs out within a day and I want a solution for this. I have tried OpenRouter with deepseek-r1 from CrewAi docs, does not work. Hugging face the same way, no luck. I’ve been trying to use LLM Studio for local llm, that too is not working. Please lmk if any of you’ve any solution. This is how I’ve been using llm to provide llm=llm in agent definition. lm = LLM( model ="openrouter/deep…