Recipe: GLM-5.2 (unpruned QuantTrio Int4-Int8Mix) at 200K ctx with MTP spec decode on a 4x NVIDIA DGX Spark (GB10) cluster
Shell Updated 4 months ago 1 commits 18 stars
zenith-bot|Mirror: tonyd2wild/GLM-5.2-QuantTrio-200K-4x-DGX-Spark (⭐18)
4 months agoAbout
Recipe: GLM-5.2 (unpruned QuantTrio Int4-Int8Mix) at 200K ctx with MTP spec decode on a 4x NVIDIA DGX Spark (GB10) cluster
Readme
18 stars
2 forks