GraySoft
Projects Models Compare Cloud benchmarks FAQ Download guIDE →

cloudyu author hub

GLM 5.3 SLIM E192 — IQ2 XXS GGUF: GLM 5.3 on a single machine GLM 5.3, the 744B parameter frontier MoE, running on one GPU or one Mac. Expert pruning 192 of 256 routed experts, "SLIM" took 25 % off the model; DwarfStar's 2 bit routed expert recipe took the rest. The result is a …

Models
4
Downloads
1,212
cloudyu/DeepSeek-V4-Flash-4Expert-GGUF
485 downloads · text-generation
cloudyu/hy3-gguf
403 downloads · text-generation
cloudyu/GLM-5.3-GGUF
179 downloads · text-generation

Run models locally with guIDE

Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.

Download guIDE → · Browse 524k+ models · Compare models