GraySoft
Projects Models Compare Cloud benchmarks FAQ Download guIDE →
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…

ggufllama.cppmoeglmreammergedtext-generationbase_model:zai-org/GLM-5.2base_model:quantized:zai-org/GLM-5.2license:mitendpoints_compatibleregion:usconversational

Runs locally from ~129.45 GB disk (32 GB+ VRAM class GPUs with llama.cpp / guIDE).

Downloads
3,318
Likes
0
Pipeline
text-generation
Author

Repository Files & Downloads

2 GGUF files detected
Direct downloads for local inference
FileTypeQuantizationSizeLink
GLM-5.2-REAM-Q2_K.ggufGGUFQ2_K129.45 GBDownload
GLM-5.2-REAM-Q3_K_M.ggufGGUFQ3_K_M169.33 GBDownload

Model Details

Model IDicecubetr/GLM-5.2-REAM-GGUF
Authoricecubetr
Pipelinetext-generation
Licensemit
Base modelzai-org/GLM-5.2
Last modified2026-07-11T09:01:29.000Z

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.

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

Source: Hugging Face · Compare models