Lab
Research, experimentation and open source: hardware, IoT, robotics, biotech and edge AI.
50 published articles
Featured3 min read
Performance
Gemma 4 runs 90% faster in Ollama 0.31 with a trick that needs no config
Ollama 0.31 introduces multi-token prediction for Gemma 4 on Apple Silicon, achieving near 90% faster token generation on coding benchmarks. The speedup comes from an auto-tuned draft model and a custom MLX kernel that eliminates redundant weight reads.
2026-06-29
6 min read
Distributed databases
Five database optimizations that turned 10-second queries into milliseconds
Large order tables in distributed databases suffer from unstable index selection, expensive table lookups, and wasted partition scans. This analysis presents five production-tested optimizations for PolarDB-X, with real-world latency drops from seconds to milliseconds.
2024-08-01