Hacker News new | ask | show | jobs
user: andreaborio
created: 2024-06-03
karma: 15

submissions:

0 points | 0 comments
Show HN: Qwen3.6-35B-A3B on a 16 GB M1 Pro with SSD-streamed MoE
24 points | 4 comments
Running GLM-5.2 on a 64GB Mac, barely
2 points | 0 comments
Re-quantizing a local LLM 14x faster by skipping the tensors that didn't change
8 points | 0 comments