Presenter walks attendees through model naming, quantization and Hugging Face searches
Matthew Tiner demonstrated how to identify and choose open models on Hugging Face (e.g., Quinn 3.8, Gemma 4), explained quantization tradeoffs (Q4, 4-bit), and described common file formats such as GGUF and MLX for local deployment.
The full story
Tiner guided attendees through searching Hugging Face for models suited to their hardware and use case, explaining how model names indicate parameter counts (e.g., "27 b") and how tags like "instruct" or "agentic" describe intended use. He emphasized testing models using consistent tasks to compare accuracy and perplexity across quantizations.
Sign up to keep reading.
Your free newsletter brings you what your city council, county, and school board discussed and decided.
Keep reading for free
Create a free account to finish this story and see the video, transcript and key details.
Continue with GoogleContinue with emailAlready have an account? Log in