UPDATE:

Due to HF storage limits, the GGUF files have been move to modelscope:

This is Q4_K_M gguf quant of AesSedai/GLM-4.6-REAP-266B-A32B

AesSedai/GLM-4.6-REAP-266B-A32B was created using REAP (Router-weighted Expert Activation Pruning), a novel expert pruning method that selectively removes redundant experts while preserving the router's independent control over remaining experts.

See the GLM-4.5-Air version by Cerebras for more details cerebras/GLM-4.5-Air-REAP-82B-A12B

The MTP tensors were not included in this quant (though llama.cpp hasn't implemented this feature anyway)

** Imatrix **

Note: currently non-functional because of missing mtp.safetensors file and entry in model.safetensors.index.json

Forked from https://github.com/CerebrasResearch/reap to https://github.com/AesSedai/reap to hack in GLM-4.6 support.

Produced with: