| user: | marcobambini |
| created: | September 13, 2014 |
| karma: | 5.2k |
| about: | https://marcobambini.com |
| 1. | GLM-5.3-Flash on Apple Silicon(github.com) |
| 2. | |
| 3. | |
| 4. | I once wrote a programming language by hand and now I feel like a dinosaur(marcobambini.substack.com) |
| 5. | Run Kimi K3 using 29 GB of RAM at 0.50 tok/s(github.com) |
| 6. | Running Kimi K3 on a local computer(github.com) |
| 7. | A new inference engine to run Kimi K3 2.78T parameter with 29GB of RAM(marcobambini.substack.com) |
| 8. | Show HN: Run Full Kimi K3 with 29 GB of RAM(github.com) |
| 9. | |
| 10. | Run Kimi K3 on a local computer(github.com) |
| 11. | |
| 12. | 32 days ago | discuss |
| 13. | Rethinking Databases for Humans and AI Agents(marcobambini.substack.com) |
| 14. | Measuring and Reducing CPU Usage in SQLite(sqlite.org) |
| 15. | SQLite Databases for Humans and Agents(marcobambini.substack.com) |
| 16. | Rethinking Databases for Humans and AI Agents(marcobambini.substack.com) |
| 17. | The Cloud vs. Edge Debate Is Over(marcobambini.substack.com) |
| 18. | Block-Level CRDT: The Missing Piece for Collaborative AI Agent Memory(marcobambini.substack.com) |
| 19. | The Cloud vs. Edge Debate Is Over(marcobambini.substack.com) |
| 20. | |
| 21. | |
| 22. |