A large model stores a great deal of knowledge. A Mixture-of-Experts model uses only a small slice of it for each word it reads — which is what lets frontier-class intelligence run on a plain server CPU, at the edge, inside your institution. This is the design behind GLM, and the blueprint for KODA's sovereign models.
Frontier models hold hundreds of billions of parameters. Loading all of them into fast memory needs a rack of GPUs — expensive, scarce, and tied to a cloud you do not control. For a hospital, a factory or a sovereign deployment, that is the wrong shape.
Mixture-of-Experts changes the economics: keep the knowledge broad, but activate only the fraction relevant to each token.
A dense model runs every parameter for every token. A MoE model has many "experts" but a router picks only a few per token — so most of the model stays idle and cheap.
GLM-5.2: 744B parameters stored · ~5.4% active per token (verified from the Colibri runtime).
For each token, a small router scores the experts and picks the top few. A shared expert always runs — it carries the general competence — while the routed experts add specialisation on top. The results are combined.
Why this design wins: the router balances expert load with a learnable bias — no auxiliary loss fighting the main objective — so experts stay balanced and quality improves. Attention is compressed too (MLA), shrinking the memory cost of long context by roughly 57×.
If only a few experts run per token, they need not all sit in expensive fast memory. A sovereign runtime treats VRAM, RAM and disk as one hierarchy: hot experts stay fast, cold experts live on NVMe, and a prefetcher predicts which experts the next layer will call and pulls them in ahead of time.
This is the Colibri runtime pattern — Apache-2.0, single-file C, zero dependencies. KODA studies it as the reference for CPU-native serving.
We do not chase a 744B model. We apply the same principles at sovereign scale: one shared base carries general competence; small identity adapters make it Koda, or a clinical or industrial specialist; governed memory holds the facts; and a CPU-native runtime serves it all — beside the equipment, inside the institution.
Runs on your own hardware. No dependence on a single GPU vendor or foreign cloud.
Each agent keeps its identity and memory across sessions — and we measure that it survives.
Every recommendation is attributable, over-rideable and recorded. Authority stays human.
Store broad, activate narrow: frontier-style capability at a fraction of the running cost.
Mixture-of-Experts is why the same idea that powers a 744-billion-parameter model also lets a governed KODA agent live on a factory-floor appliance or a hospital's own server. Frontier design — brought down to where the work actually happens.
Honest boundary: figures cited (744B / ~5.4% active / ~57× KV / ~72% routing predictability) are verified from the GLM-5.2 architecture and the Colibri runtime. KODA's sovereign models are in the Track-D research and product programme — not a claim of a finished product.