Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦
C
Merge dev: keep the softened oracle expectation, on the current binary name
JustVuggc154cf24496f
diff --cc docs/windows.mdindex e203f68c,153ead0c..43c54203--- a/docs/windows.md+++ b/docs/windows.md@@@ -121,10 -121,10 +121,10 @@@ make colibri.exe ARCH=nativ# Verify (tiny model, 2.4 MB):pip install torch transformers safetensors huggingface_hubpython tools/make_glm_oracle.py # generate tiny oracle- SNAP=./glm_tiny TF=1 ./glm.exe 64 16 16 # expect "~30-32/32 positions"-SNAP=./glm_tiny TF=1 ./colibri.exe 64 16 16 # expect "32/32 positions"++SNAP=./glm_tiny TF=1 ./colibri.exe 64 16 16 # expect "~30-32/32 positions"# Run with real model:- SNAP=D:\glm52_i4 ./glm.exe 64 4 16 # batch inference+ SNAP=D:\glm52_i4 ./colibri.exe 64 4 16 # batch inferencepython coli chat --model D:\glm52_i4 # interactive chatpython coli serve --model D:\glm52_i4 # OpenAI-compatible API```