moe-pruning on Hacker News: 1 stories with screenshots

Screenshot of github.com: Show HN: Maple – Sub-2-BPW Moe Pruning to Run Gemma 4 26B at 45 TPS on a 6GB GPU

Show HN: Maple – Sub-2-BPW Moe Pruning to Run Gemma 4 26B at 45 TPS on a 6GB GPU (github.com)

7 points by AmSach 5 days ago | 3 comments

GitHub repository for MAPLE, a Mixture-of-Experts pruning framework that compresses Gemma 4 26B-A4B to a 4.75 GB GGUF to run fully in VRAM on 6 GB GPUs.

moe-pruning gemma llm-quantization gguf

#moe-pruning on Hacker News

Show HN: Maple – Sub-2-BPW Moe Pruning to Run Gemma 4 26B at 45 TPS on a 6GB GPU(github.com)

Show HN: Maple – Sub-2-BPW Moe Pruning to Run Gemma 4 26B at 45 TPS on a 6GB GPU (github.com)