Model Intelligence Sheet
icecubetr/GLM-5.2-REAM-GGUF overview
GLM 5.2 REAM GGUF What this is Base: coder3101/GLM 5.2 REAM https://huggingface.co/coder3101/GLM 5.2 REAM which was removed after I downloaded it, which is bas…
Runs locally from ~129.45 GB disk (32 GB+ VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
Model Details
| Model ID | icecubetr/GLM-5.2-REAM-GGUF |
|---|---|
| Author | icecubetr |
| Pipeline | text-generation |
| License | mit |
| Base model | zai-org/GLM-5.2 |
| Last modified | 2026-07-11T09:01:29.000Z |
Model README
---
license: mit
base_model:
- zai-org/GLM-5.2
base_model_relation: quantized
pipeline_tag: text-generation
tags:
- gguf
- llama.cpp
- moe
- glm
- ream
- merged
---
GLM-5.2-REAM-GGUF
What this is
- Base: coder3101/GLM-5.2-REAM which was removed after I downloaded it, which is based on zai-org/GLM-5.2 (
glm_moe_dsa, ~753B MoE). - Runs as full MLA attention (the DSA lightning-indexer is not used at inference — same simplification as the upstream conversion).
- Quantized using llama.cpp.
Recommended serving — recover most of the loop gap for free
- Anti-loop (recommended):
- min_p=0.05, repetition_penalty=1.05
- min_p=0.05, repetition_penalty=1.10
Start at 1.05; go to 1.10 if you see loops — a higher repetition penalty trades a little risk of
over-penalizing legitimate repetition (e.g. in code) for near-zero looping.
Run icecubetr/GLM-5.2-REAM-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models