Termsslug: bits-per-weight

Bits Per Weight

比特每权重

A metric for the average number of bits each parameter occupies after quantization or compression; lower values mean smaller mod

Curated Intelligence

1 items · Page 1/1
Hacker News AIT2·Open Source
62 pts
MAPLE Pruning Runs Gemma 4 26B at 45 TPS on a 6GB GPU

An independent researcher released MAPLE, a structural pruning method for mixture-of-experts LLMs that removes dormant experts, shrinking Gemma 4 26B-A4B from 9.92 GB to 4.75 GB (about 1.48 bits per parameter) so it runs entirely in 6 GB of laptop VRAM at 45.4 tokens per second. The checkpoint is specialized for Python coding and STEM reasoning, and the pipeline is claimed to be domain-agnostic.