Stories by marcobambini

GLM-5.3-Flash at 3.3 tok/s

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

I once wrote a programming language by hand and now I feel like a dinosaur

Run Kimi K3 using 29 GB of RAM at 0.50 tok/s

Running Kimi K3 on a local computer

A new inference engine to run Kimi K3 2.78T parameter with 29GB of RAM

Show HN: Run Full Kimi K3 with 29 GB of RAM

Show HN: A new engine to run Kimi K3 on a laptop

Run Kimi K3 on a local computer

Rethinking Databases for Humans and AI Agents

Measuring and Reducing CPU Usage in SQLite

SQLite Databases for Humans and Agents

Rethinking Databases for Humans and AI Agents

The Cloud vs. Edge Debate Is Over

Block-Level CRDT: The Missing Piece for Collaborative AI Agent Memory

The Cloud vs. Edge Debate Is Over

SQLite-Vector now with Google TurboQuant for a 38x speedup

Show HN: SQLite-Columnar – Columnar Storage for SQLite

SQLite Columnar: Column-oriented extension for SQLite up to 130,000x faster

Show HN: SQLite-columnar, a column-oriented analytics extension for SQLite

1 2 3 4 5 6 7