Live data from Hacker News

Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model

github.com

61–70 of 255 posts

Re: Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model

#62

I 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…

Sounds cool, play with it and let uk know what you think!

Re: Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model

#63
post #59

I 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?

It is for building agentic capabilities into very small devices like phones, glasses, watches and more. Does that make sense?

Re: Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model

#65
post #64

From 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?

Gemini is pretty solid for 1-shot tool call and affordable as well.
Post reply on HN