Gemma, every mention

15 scenes, the whole family · ← back to Gemma

tap a year for its mentions
0020140220252026episodesmentions
01220252026episodes it came up in
0010120220252026episodesmentions per episode

every year anyone Greg Isenberg 31Logan Kilpatrick 1

Verbatim, from the transcripts: the passages where Gemma comes up

loading…

I'm Obsessed With Local AI. Here's Why Sep 8, 2026 · 29 mentions

  • ▶ 0:29 Greg Isenberg By the end of today's episode, you're going to understand what local AI is, when it matters, how to run open models at work, where Hugging Face fits in here, which Gemma model I'd start with, how I'd run a model locally with LM Studio or… 2 times in the scene
  • ▶ 3:17 Greg Isenberg That could be something like Gemma, Llama, or Mistral.
  • ▶ 3:46 Greg Isenberg Gemma is a model family. 2 times in the scene
  • ▶ 9:56 Greg Isenberg Gemma is Google's open model family, and Google's a trusted brand.
  • ▶ 10:44 Greg Isenberg So, Gemma is Google's family of open models, and Gemma IV is built for the efficient, local, and on-device use. 6 times in the scene
  • ▶ 10:44 Greg Isenberg So, Gemma is Google's family of open models, and Gemma IV is built for the efficient, local, and on-device use.
  • ▶ 12:19 Greg Isenberg Then you have Gemma Scope, which is more understanding how models work under the hood.
  • ▶ 14:21 Greg Isenberg Beyond Google Gemma, I'll give you a quick primer on the other
  • ▶ 18:20 Greg Isenberg Like, if you actually want to run Gemma, here's how I would do it. 4 times in the scene
  • ▶ 18:31 Greg Isenberg You search for Gemma IV. 4 times in the scene
  • ▶ 22:01 Greg Isenberg But if you have something like 16 gigabytes of RAM, you can do some useful experiments with models like E-IVB and smaller quantized models.
  • ▶ 23:22 Greg Isenberg Then I would run a local model like Gemma and ask it to create a file called what customers are telling us .md, the markdown file. 3 times in the scene
  • ▶ 35:07 Greg Isenberg It could be anything from sales calls or meeting transcripts, old tweets, ideas that you have, then run Gemma, whatever model you choose, 2 times in the scene

Claude Fable 5 is BANNED. What to do? Jun 13, 2026 · 2 mentions

Google AI studio replaces your AI tech stack (full demo) Feb 15, 2025 · 1 mention

  • ▶ 7:20 Logan Kilpatrick Uh, there's some Gemma, which is our open source version of the models for folks who need open source models.
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 300 episodes transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.