Gemma, every mention
3 scenes · ← back to Gemma
tap a year for its mentions
every year anyone Garry Tan 4Demis Hassabis 2
Verbatim, from the transcripts: the passages where Gemma comes up
Multi-GPU Kernels, Intelligence per Watt, Heterogeneous Inference, and More | YC Paper Club · Y Combinator
- ▶ 25:43 unnamed speaker We did about twenty-plus different state-of-the-art local models, um, across GEMMA, GBD OSS, QUAN, IBM Granite, all in the range of one to two hundred billion parameters, some MOE, some dense.
Demis Hassabis: Agents, AGI & The Next Big Scientific Breakthrough · Y Combinator
- ▶ 10:18 Demis Hassabis And you also see some of that goodness in our Gemma models, which hopefully you're all enjoying our Gemma four models, which I think are really amazing power for their sizes. 2 times in the scene
- ▶ 20:24 Garry Tan I mean, the recent release of Gemma, you're making highly capable, open and accessible ones that can actually run locally. 4 times in the scene