HN Explorer

marcobambini

↗ HN profile [ 98.2 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. Run DeepSeek v4.1 Flash on your Mac (github.com)
    2 points 1
  2. Show HN: Warp – Run DeepSeek v4.1 Flash with 5 GB of RAM at 3.77 tok/s (github.com)
    1 points 5
  3. 1 points 0
  4. Show HN: SQLite-Vector – Vector search for SQLite, now Apache 2.0 (github.com)
    2 points 0
  5. SQLite-Vector is now licensed under Apache 2.0 (github.com)
    3 points 0
  6. GLM-5.3-Flash on Apple Silicon (github.com)
    1 points 0
  7. GLM-5.3-Flash at 3.3 tok/s

    A few months ago, I created the WARP engine (formerly WASTE) to run Kimi K3, the complete 2.78-trillion-parameter model, on macOS. GLM-5.3-Flash shares many architectural similarities with Kimi K3, so I added support…

    1 points 0
  8. Show HN: Warp – Run the 313B GLM-5.3-Flash on a MacBook with 8GB RAM

    A few months ago, I created the WARP engine (formerly WASTE) to run Kimi K3, the complete 2.78-trillion-parameter model, on macOS. GLM-5.3-Flash shares many architectural similarities with Kimi K3, so I added support…

    1 points 1
  9. I once wrote a programming language by hand and now I feel like a dinosaur (marcobambini.substack.com)
    3 points 1
  10. Run Kimi K3 using 29 GB of RAM at 0.50 tok/s (github.com)
    341 points 47
  11. Running Kimi K3 on a local computer (github.com)
    2 points 0
  12. A new inference engine to run Kimi K3 2.78T parameter with 29GB of RAM (marcobambini.substack.com)
    4 points 2
  13. Show HN: Run Full Kimi K3 with 29 GB of RAM (github.com)
    9 points 2
  14. Show HN: A new engine to run Kimi K3 on a laptop

    Kimi K3 has 2.78 trillion parameters and ships as 1.42 TB of weights. It clearly does not fit in the memory of a laptop. But K3 is a Mixture-of-Experts model. For each token, only a small fraction of its 896 experts per…

    7 points 2
  15. Run Kimi K3 on a local computer (github.com)
    8 points 0
  16. 1 points 0
  17. Rethinking Databases for Humans and AI Agents (marcobambini.substack.com)
    3 points 0
  18. Measuring and Reducing CPU Usage in SQLite (sqlite.org)
    2 points 0
  19. SQLite Databases for Humans and Agents (marcobambini.substack.com)
    3 points 0
  20. Rethinking Databases for Humans and AI Agents (marcobambini.substack.com)
    2 points 0
  21. The Cloud vs. Edge Debate Is Over (marcobambini.substack.com)
    4 points 1
  22. Block-Level CRDT: The Missing Piece for Collaborative AI Agent Memory (marcobambini.substack.com)
    2 points 0
  23. The Cloud vs. Edge Debate Is Over (marcobambini.substack.com)
    2 points 1
  24. SQLite-Vector now with Google TurboQuant for a 38x speedup (github.com)
    3 points 0
  25. Show HN: SQLite-Columnar – Columnar Storage for SQLite (github.com)
    4 points 0