HN Explorer

andreaborio

↗ HN profile [ 29.3 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. Show HN: Qwen3.6-35B-A3B on a 16 GB M1 Pro with SSD-streamed MoE (github.com)
    24 points 7
  2. Running GLM-5.2 on a 64GB Mac, barely (andreaborio.substack.com)
    2 points 0
  3. Re-quantizing a local LLM 14x faster by skipping the tensors that didn't change (andreaborio.substack.com)
    8 points 0
  4. 1 points 0