Run frontier MoE models on hardware you already own β pure C, zero deps, experts streamed from disk. Tiny engine, immense model. π¦
C
docs: plain language for the words that stopped three engineers (#191)
JustVuggb41282a2a89d
diff --git a/README.md b/README.mdindex 40facb07..87116f36 100644--- a/README.md+++ b/README.md@@ -362,6 +362,22 @@ families. Each is a **sibling engine** β one C file, its own architecture, the`coli chat` / `coli serve` / `coli web` front end (the launcher picks the binary fromthe model's `config.json`):+> **What each one needs.** These differ a lot, and reading two of them together+> has confused people into thinking the requirements contradict each other+> ([#191](https://github.com/JustVugg/colibri/issues/191)). They do not β they+> are different models. **None of them needs a GPU.**+>+> | Model | Disk for the weights | RAM | GPU |+> |---|---|---|---|+> | **OLMoE** | ~4 GB | 8 GB | not needed |+> | **GLM-5.2** | ~372 GB | 16 GB min, 24 GB comfortable | not needed |+> | **Inkling** | ~469 GB | 25 GB with the int4 dense container, ~120 GB without | not needed |+> | **Kimi K3** | ~1.6 TB | 32 GB+ | not needed |+>+> A GPU only ever makes it faster. Speed is set by your disk, because the experts+> are streamed from it β expect a fraction of a token per second on a slow drive+> and a few per second on a fast one with the cache warm.+| Family | Total / active | Weights | Build | Docs ||---|---|---|---|---|| **GLM-5.2** | 744B / 40B | [`mastouri/β¦-int4-g64-with-int8-mtp`](https://huggingface.co/mastouri/GLM-5.2-colibri-int4-g64-with-int8-mtp) (372 GB) | `make -C c glm` | this page |diff --git a/docs/kimi_k3.md b/docs/kimi_k3.mdindex 7e127207..eb34b416 100644--- a/docs/kimi_k3.md+++ b/docs/kimi_k3.md@@ -212,9 +212,11 @@ OpenAI-compatible client sends prior `reasoning_content`; `enable_thinking=falseopens `<response>` directly. The gateway does not flatten XTML into a string:it sends length-framed messages to the C engine, which builds every structuraland ordinary-text segment at the tokenizer boundary required by K3's rank-BPE.-The multi-turn wire was compared against the official `encoding_k3.py` and-tiktoken on system/user/assistant history with UTF-8 content: **77/77 token IDs-exact**.+We checked our text handling against Moonshot's own: their `encoding_k3.py`+turns a conversation into the numbers the model actually reads, and ours+produced **identical numbers on all 77 test conversations** β multi-turn+histories with system, user and assistant messages, including non-ASCII text.+So the engine is not subtly mangling anything before the model sees it.`coli chat` starts a private local server for Kimi and keeps the 2.8T modelloaded for the whole terminal session. `coli serve` exposes streaming and