What is the use case for this?
Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model
61–70 of 255 posts
Re: Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model
#62I source old, defective high-end radios with timeless designs from brands like Grundig or Braun, and replace the original hardware with a Raspberry Pi while using the original audio parts to build custom smart speakers. Reliable hotword detection and voice command recognition have been a persistent challenge over the years, but whisper and other small models have helped enormously. At the moment I have ollama running…
Re: Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model
#63I don't really understand what this is for... there is a lot of ML-researcher talk on the GH page about the model architecture, but how should I use it? Is it a replacement for Kimi 2.7, Claude Haiku, Gemini Flash 3.1 lite, a conversational LLM for the situations where it's mostly tool-calling like coding and conversational AI?
Re: Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model
#64Re: Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model
#65From all the models that do toolcalls the only thing I am confused is why did you pick the worst? Or maybe they are only bad in agentic work it fine for one shot toolcalls?
Re: Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model
#66Re: Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model
#67This is some excellent work Henry! Very excited to try it out.
Re: Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model
#68Re: Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model
#69That M versus B is way too subtle. 0.026B is my suggestion