Show HN: Maple – Sub-2-BPW Moe Pruning to Run Gemma 4 26B at 45 TPS on a 6GB GPU
Article URL: https://github.com/AmSach/maple Comments URL: https://news.ycombinator.com/item?id=50410253 Points: 3 # Comments: 1
This is a summary aggregated from Hacker News. Read the complete article on the original site:
Read full article at Hacker News