Jul 14, 2026 · Artificial Intelligence

How Colibri Runs a 744 B MoE Model on CPU with Only 25 GB RAM

Colibri demonstrates that the 744‑billion‑parameter GLM‑5.2 MoE model can be executed on a pure‑CPU system using roughly 25 GB of memory by streaming expert weights from disk, int4‑quantizing dense parameters, and employing a compact C inference engine.

CPU inferenceGLM-5.2MLA attention

0 likes · 7 min read

How Colibri Runs a 744 B MoE Model on CPU with Only 25 GB RAM

Alibaba Cloud Developer

Feb 7, 2025 · Artificial Intelligence

Why DeepSeek V3 Achieves Low Training Costs: Inside Its AI Innovations

This article provides a comprehensive analysis of DeepSeek's large‑language‑model technology, covering the company's background, model capabilities, remarkably low training and inference costs, and the core architectural and algorithmic innovations such as MoE, MLA attention, FP8 mixed‑precision, and the DualPipe pipeline that enable efficient large‑scale AI deployment.

AI architectureDeepSeekFP8 training

0 likes · 19 min read

Why DeepSeek V3 Achieves Low Training Costs: Inside Its AI Innovations

MLA attention

How Colibri Runs a 744 B MoE Model on CPU with Only 25 GB RAM

Why DeepSeek V3 Achieves Low Training Costs: Inside Its AI Innovations

How Colibri Runs a 744 B MoE Model on CPU with Only 25 GB RAM