https://mattiaperetti.it/blog Senior backend engineer writing about backend architecture, application security, and the shift toward agentic AI systems. en-us undefined (Mattia Peretti) undefined (Mattia Peretti) Fri, 17 Jul 2026 00:00:00 GMT https://mattiaperetti.it/blog/local-llm-tipping-point https://mattiaperetti.it/blog/local-llm-tipping-point Colibrì, a ~1,300-line pure C inference engine with zero dependencies, runs the 744B-parameter GLM 5.2 MoE model on a laptop with 25 GB of RAM and no GPU by streaming int4-quantized experts from NVMe. Cold-cache throughput is 0.05 to 0.1 tokens per second, so speed is the honest limiter, but it is an existence proof that frontier-scale local inference works on commodity hardware. Fri, 17 Jul 2026 00:00:00 GMT undefined (Mattia Peretti) aillmlocal-llmopen-sourceinference