Skip to content
Topic

#Ternary Quantization

1 article on Ternary Quantization — news, releases, guides and analysis from the SourceFeed engine.

How a 20B Model Hits 120 tok/s on an iPhone
Article 1h ago 0

How a 20B Model Hits 120 tok/s on an iPhone

DeepGrove's Maple-Preview stacks native ternary training on MoE sparsity, and the arithmetic largely holds up.

Priya Nair