Gemma
GoogleVerified via Wikidata
family of lightweight open models designed by Google
Mentioned in 28 videos
Published
February 21, 2024
Developer
Google
What podcasters actually say about Gemma.
28 mentions, no marketing. Save them all to a pod and ask any question.
Common Themes
Videos Mentioning Gemma
The Inference Frontier: from 100 to 10,000 tokens per second — Sean Lie, Cerebras CTO
Latent Space
A medium-sized model that is expected to run at speeds up to 10,000 TPS on the upcoming Cerebras CS5, showcasing the advancements in inference speed.
Open Models Are Collapsing The Cost Of AI
Y Combinator
AI models from DeepMind that are suitable choices for local deployment.
Why The Harness Matters More Than The Model | YC Paper Club
Y Combinator
A language model that can be used as the engine for Open Jarvis.
Workshop: Building and optimizing dictation features
AssemblyAI
A more intelligent model from Quinn that can be used for dictation, though it may come with increased latency.
PreviousPage 2 of 2