On July 1, 2026, developer JustVugg released Colibri, a 14,700-line pure-C inference engine that runs GLM-5.2, a 744-billion-parameter Mixture-of-Experts model, on 25GB of RAM with no GPU, using an LR…
A new weight reordering technique for Mixture-of-Experts (MoE) models optimizes physical file layout to minimize NVMe seek overhead, achieving massive gains in explicit-read inference engines like MLX…
A developer has open-sourced UGR, an AI runtime operating system designed to orchestrate inference across commodity hardware by treating models as collections of resources that can move between memory…
Colibri, an open-source inference system, runs the 744-billion-parameter GLM-Z1-Rumination model on a consumer laptop by using a three-tier memory system that treats NVMe SSD as an extension of GPU me…
A developer discovered Colibri, a project that runs massive Mixture of Experts models on ordinary CPUs and SSDs by loading only needed experts into memory. The developer proposes a proactive caching s…
A developer known as JustVugg built Colibri, a pure C inference engine that runs the 744-billion-parameter GLM-5.2 model on a laptop with 25 GB of RAM by streaming experts from disk instead of loading…
A developer known as Nokka built Colibri, a pure C inference engine (~2,400 lines, zero dependencies) that runs the 744B-parameter GLM-5.2 Mixture-of-Experts model on a consumer machine with only 25 G…