---
license: mit
base_model: zai-org/GLM-5.2
base_model_relation: quantized
pipeline_tag: text-generation
library_name: gguf
tags: [gguf, llama.cpp, moe, glm, reap, pruned]
---

# 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% perplexity vs full GLM-5.2) **with 2-bit Q2_K**. It **works but is delicate**:
- ✅ Coherent with sampling: *"The capital city of France … is Paris."*
- ❌ **Collapses into repetition (`* * * *`) with greedy / temp 0 decoding.**

**Use these sampler settings** (or it may loop):
```
--temp 0.6 --repeat-penalty 1.1 --top-p 0.95
```
If you can spare the VRAM, the **[Q3_K_M build](https://huggingface.co/pipenetwork/GLM-5.2-REAP50-Q3_K_M-GGUF)** (~169 GB) is noticeably more robust. For real quality, use the MLX REAP-25 (+2.3% PPL) or full GLM-5.2.

## Requires a patched llama.cpp
Stock llama.cpp can't load GLM-5.2 GGUFs yet (DSA indexer required on every layer; GLM-5.2 ships it on only some). Apply the included `llama.cpp-glm-dsa-indexer-optional.patch` (or wait for [ggml-org/llama.cpp#24770](https://github.com/ggml-org/llama.cpp/pull/24770)), rebuild, then:
```bash
./build/bin/llama-cli -m GLM-5.2-REAP50-Q2_K-00001-of-00004.gguf --jinja -ngl 99 \
  --temp 0.6 --repeat-penalty 1.1 -p "..."
```

REAP-50 = top-128 of 256 experts/layer by saliency; runs as full MLA attention. Smoke-tested on Metal (~20 tok/s).