pipenetwork author hub
GLM 5.2 REAP50 Q2 K GGUF GGUF of GLM 5.2, REAP expert pruned 50% + Q2 K ~129 GB — the maximum context option for 2× 96 GB GPUs 192 GB , leaving ~60 GB for KV cache ≈2.5× the context room of the Q3 K build . ⚠️ Quality: fragile — most degraded variant This stacks REAP 50 ~+37.5% …
Models
2
Downloads
0
Run models locally with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.